2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,282[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1000x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1000x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1000x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1000x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1000x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x2688x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+16
2x1000x1x1x1x1x1x1x2688x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1000x1x1x1x1x1x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x1000x1x1x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x1000x1x1x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+16
2x1000x1x1x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1000x1x1x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1000x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+8
2x1000x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1000x1x1x1x1x1x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1000x1x1x1x1x1x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1000x1x1x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+8
2x1000x1x1x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1001x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x1001x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1001x1x1x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x1001x1x1x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1001x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x1001x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1002x14x14x1x1x1x1x190x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1002x1x1x1x1x1x1x83x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1002x64x64x1x1x1x1x190x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1002x64x64x1x3x3x1x1002x1x1x1x0x1x1x0x1x1x0x0x1002xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1002x7x7x1x1x1x1x182x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1002x7x7x1x1x1x1x182x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1008x128x128x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1008x128x128x1x3x3x1x1008x1x1x1x0x1x1x0x1x1x0x0x1008xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1008x128x128x1x3x3x1x1008x1x1x1x0x2x2x0x1x1x0x0x21xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1008x14x14x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1008x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1008x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1008x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1008x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1008x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1008x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1008x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1008x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1008x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1008x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1008x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1008x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1008x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1008x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1008x14x14x1x3x3x1x1008x4x1x1x0x1x1x0x1x1x0x0x1008xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1008x21x21x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1008x256x256x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1008x32x32x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1008x42x42x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1008x64x64x1x3x3x1x1008x4x1x1x0x1x1x0x1x1x0x0x21xNCHWxFP16xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1008x7x7x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1008x7x7x1x3x3x1x1008x4x1x1x0x1x1x0x1x1x0x0x21xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x100x128x128x1x1x1x1x600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x100x128x128x1x7x7x1x100x1x3x3x0x1x1x0x1x1x0x0x100xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x100x128x128x1x7x7x1x100x4x3x3x0x1x1x0x1x1x0x0x100xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x100x14x14x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x100x1x1x1x4x4x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x100x1x1x1x4x4x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x100x1x1x1x4x4x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x100x1x1x1x4x4x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x100x1x1x1x4x4x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x100x1x1x1x4x4x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x100x3x3x1x4x4x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x100x3x3x1x4x4x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x100x3x3x1x4x4x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x100x3x3x1x4x4x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x100x3x3x1x4x4x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x100x3x3x1x4x4x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1010x1x1x1x1x1x1x11110x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1010x1x1x1x1x1x1x4040x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1016x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1016x64x64x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x101x128x128x1x3x3x1x25x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x101x256x256x1x3x3x1x25x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x1022x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x1024x1008x1008x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1008x1008x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1008x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1008x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1008x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1008x1040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1008x1040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1008x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1008x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1008x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x1024x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1008x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1040x1008x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1040x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1040x1040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1040x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1040x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x10x10x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x10x10x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x111x111x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x111x111x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x111x111x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x111x111x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x111x111x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x112x112x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x112x112x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x112x112x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x112x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x112x144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x112x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x113x113x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x113x113x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x113x113x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x113x113x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x113x113x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x126x126x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x128x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x128x128x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x128x128x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x8192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x128x128x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x128x128x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x128x128x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x128x128x1x3x3x1x1024x4x2x2x0x2x2x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x128x128x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x128x128x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x128x128x1x5x5x1x1024x4x2x2x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x128x128x1x7x7x1x1024x4x3x3x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1024x12x12x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x12x12x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x12x12x1x3x3x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x12x12x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x12x12x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x12x12x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x12x12x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1024x12x12x1x3x3x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x12x12x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x13x13x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x13x13x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x13x13x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x2048x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x13x13x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x13x13x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x13x13x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x1x1x21x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x13x13x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x13x13x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x13x13x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+2
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1024x13x13x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x13x13x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x13x13x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x13x13x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x13x13x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x1024x13x13x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1024x13x13x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x13x13x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x13x13x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x13x13x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x1432x1432x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1432x1464x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1433x1433x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1433x1465x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1448x1448x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x144x112x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x144x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x144x144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x144x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x1464x1432x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1464x1464x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1465x1433x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1465x1465x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x146x146x1x9x9x1x1024x1x4x4x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x147x147x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,52;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,48;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,48;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:246
2x1024x14x14x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x14x14x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:172
2x1024x14x14x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:168
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:215
2x1024x14x14x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:192
2x1024x14x14x1x1x1x1x2048x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x1024x14x14x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x1024x14x14x1x1x1x1x2048x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:206
2x1024x14x14x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x1024x14x14x1x1x1x1x2048x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:238
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:219
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];TransposedConvBinWinoRxS<3-2>:97
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];TransposedConvBinWinoRxS<3-2>:108
2x1024x14x14x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:116
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:110
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:230
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:218
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:233
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:223
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:209
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];TransposedConvBinWinoRxS<3-2>:235
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];TransposedConvBinWinoRxS<3-2>:235
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,316[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];TransposedConvBinWinoRxS<3-2>:178
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];TransposedConvBinWinoRxS<3-2>:160
2x1024x14x14x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:230
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:203
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:60
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:66
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:253
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:251
2x1024x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x1024x14x14x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:233
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x1024x14x14x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:192
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:192
2x1024x14x14x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:254
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:237
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:246
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:214
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:240
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:240
2x1024x14x14x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:249
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:227
2x1024x14x14x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x1024x14x14x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:232
2x1024x14x14x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:207
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:221
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:200
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43
2x1024x14x14x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:228
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:224
2x1024x14x14x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x1024x14x14x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:249
2x1024x14x14x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x1024x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;TransposedConvBinWinoRxS<3-2>:251
2x1024x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x1024x14x14x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x1024x14x14x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:244
2x1024x14x14x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:252
2x1024x14x14x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:214
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:232
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x1024x14x14x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:155
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:125
2x1024x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:238
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:229
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51
2x1024x14x14x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1024x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x1x1x21x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x14x14x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[4];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x14x14x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x14x14x1x3x3x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x1536x1536x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x1536x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x1536x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x15x15x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x15x15x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x15x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x15x15x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,316[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x15x15x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x15x15x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x15x15x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x15x15x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x15x15x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x15x15x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x16x16x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x16x16x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x16x16x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1024x16x16x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x16x16x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x16x16x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x16x16x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x16x16x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x16x16x1x9x9x1x1024x1x4x4x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x1024x17x17x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x17x17x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x17x17x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x17x17x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x17x17x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x17x17x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x17x17x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x199x271x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x199x271x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x199x303x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x199x303x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x1x1x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1001x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1024x1x1x1x1x1x1x1001x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1024x1x1x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,324[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+-1
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+1
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:32
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,52;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x1024x1x1x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x1x1x1x1x1x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x1x1x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+16
2x1024x1x1x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,5,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,5,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,104;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x1x1x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x1x1x1x7x7x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+128
2x1024x1x1x1x7x7x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x1024x1x1x1x7x7x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x1x1x1x7x7x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x1x1x1x7x7x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x1024x1x1x1x7x7x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x1024x1x1x1x7x7x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x1x1x1x7x7x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[5];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x1024x1x1x1x7x7x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x1x1x1x7x7x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,6,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+128
2x1024x1x1x1x7x7x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x200x272x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x200x304x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x2048x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x2048x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1024x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x223x199x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x223x199x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x224x200x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x23x23x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x23x23x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x1024x23x23x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x240x240x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x240x240x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x240x240x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x240x272x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x240x272x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x240x272x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x24x24x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x24x24x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x24x24x1x2x2x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x24x24x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x1024x24x24x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x24x24x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x24x24x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x255x255x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x255x255x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x255x255x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x255x255x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x255x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x255x255x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x255x255x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x255x255x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x255x255x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x255x255x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x255x255x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x256x256x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x1024x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x1024x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x1024x256x256x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1024x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,0,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1024x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x1024x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x1024x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x256x256x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x256x256x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x1024x25x25x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x1024x25x25x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x1024x25x25x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x272x240x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x272x240x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x272x240x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x272x272x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x272x272x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x272x272x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x27x27x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x27x27x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x27x27x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x27x27x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x27x27x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x27x27x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1024x27x27x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x27x27x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1024x27x27x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x27x27x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x27x27x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x27x27x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,96[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x27x27x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x1024x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x1024x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,65[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x28x28x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x29x29x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x29x29x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x29x29x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+32
2x1024x29x29x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x29x29x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x29x29x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x29x29x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x29x29x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x29x29x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x29x29x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x29x29x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x29x29x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x29x29x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x30x30x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x30x30x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x30x30x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x30x30x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x30x30x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x30x30x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x30x30x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1024x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x31x31x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x31x31x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+32
2x1024x31x31x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x31x31x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x31x31x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x31x31x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x31x31x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x32x32x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x32x32x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x32x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x32x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x32x32x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x32x32x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1024x32x32x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x32x32x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x32x32x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x36x84x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x36x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x36x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x36x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x36x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x36x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x36x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x39x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x51x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x51x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x53x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x57x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x59x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x61x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x65x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x65x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x39x67x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x67x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x39x69x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x71x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x71x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x39x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x75x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x39x77x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x39x77x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x39x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x39x83x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x40x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x40x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x40x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x40x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x40x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x40x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x52x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x54x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x54x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x54x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x54x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x40x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x40x58x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x40x60x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x60x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x40x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x40x62x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x40x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x66x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+4
2x1024x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x40x68x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x70x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x40x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x72x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x72x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x40x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x40x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x40x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x40x76x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x40x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x40x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x40x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x78x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x40x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x40x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x40x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x40x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x40x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x40x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x40x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x40x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x40x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x40x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x41x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x51x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x51x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x53x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x59x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x61x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x41x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x65x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x67x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x67x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x69x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x41x71x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x41x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x41x73x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x77x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x41x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x81x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x41x81x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x41x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x41x83x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x42x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x42x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x42x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x42x52x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x52x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x52x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x52x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x42x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x42x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x56x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x42x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x42x58x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x42x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x60x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x42x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x42x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x42x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x42x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x64x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x42x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x42x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x42x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x66x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x42x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x68x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x42x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x42x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x42x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x42x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x42x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x78x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x42x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,48[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x42x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x42x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x42x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x82x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x42x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x42x84x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x42x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x42x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x42x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x42x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x42x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x42x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x42x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x42x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x42x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x43x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x43x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x43x59x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x43x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x61x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x65x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x43x67x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x43x69x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x71x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x43x71x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x43x73x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x75x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x43x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x77x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x77x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x43x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x43x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x43x83x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x1024x44x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x44x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x44x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x44x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x44x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x60x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x60x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x60x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x44x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x66x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x66x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x66x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x66x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x44x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x66x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x66x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x66x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x72x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x44x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x44x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x44x76x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x44x78x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x44x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x44x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x44x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x44x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x44x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x44x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x44x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x44x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x44x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x45x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x45x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x53x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x45x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x45x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x45x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x45x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x45x65x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x65x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x45x67x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x45x67x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x69x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x45x69x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x71x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x73x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x75x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x45x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x77x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x77x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x45x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x81x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x45x81x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x45x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x46x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x46x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x46x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x46x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x46x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x46x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x46x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x46x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x46x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x46x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x46x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x62x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x62x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x46x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x66x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x68x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x70x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x70x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x70x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x46x70x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x70x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x46x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x70x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x70x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x70x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x46x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x46x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x46x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x46x74x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x46x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x46x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x46x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x46x76x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x46x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x78x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x46x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x46x82x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x82x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x46x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x46x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x46x84x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x46x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x46x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x46x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x46x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x46x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x47x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x51x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x51x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x53x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x47x57x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x47x59x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x47x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x61x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x47x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x65x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x65x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x67x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x67x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x69x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x69x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x71x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x71x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x73x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x75x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x77x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x77x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x81x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x81x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x47x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x47x83x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x48x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x48x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x48x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x48x1x2x2x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x48x48x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x48x48x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x48x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x48x52x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x48x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x48x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x58x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x58x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x58x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x48x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x60x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x48x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x64x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x48x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x66x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x68x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x70x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x48x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x48x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x72x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x72x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x48x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x72x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x74x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x1024x48x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x74x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x48x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x76x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x48x78x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x78x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x48x78x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x78x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x78x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x78x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x78x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x78x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x48x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x48x80x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x48x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x80x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x80x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x48x80x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x48x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x48x80x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x48x80x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x82x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x48x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x48x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x48x84x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x48x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x48x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x48x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x48x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x48x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x48x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x48x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x496x496x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x496x528x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x49x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x49x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x49x49x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x49x53x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x53x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x49x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x59x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x59x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x61x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x63x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x65x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x49x65x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x67x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x67x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x69x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x49x73x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x49x73x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x75x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x75x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x75x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x77x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x79x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x79x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x81x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x81x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x49x83x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x49x83x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x4x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+-1
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+-1
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 1, 1, 1>+32
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x4x4x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,5,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,5,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x4x4x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x50x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x50x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x50x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x50x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x50x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x50x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x50x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x50x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x54x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x60x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x50x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x62x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x50x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x64x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x50x66x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x50x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x68x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x68x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x50x68x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x68x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x50x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x68x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x68x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x68x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x50x70x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x50x74x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x50x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x76x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x76x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x76x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x76x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x76x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x76x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x76x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x50x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x50x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x50x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x80x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x50x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x50x82x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x82x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x82x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x50x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x50x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x50x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x50x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x50x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x50x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x50x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x50x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x50x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x50x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x512x512x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x512x512x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256
2x1024x512x512x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x512x512x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x512x512x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:236
2x1024x512x512x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x512x512x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x512x512x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x51x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x51x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x51x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x51x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x51x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x51x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x51x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x51x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x528x496x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x528x528x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x52x40x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x52x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x52x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x52x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x52x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x52x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x52x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x52x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x52x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x52x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x52x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x52x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x52x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x52x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x52x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x52x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x52x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x52x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x52x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x52x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x52x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x52x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x53x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x53x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x53x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x53x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x53x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x53x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x53x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x53x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x1024x53x53x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x53x53x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x1024x53x53x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x53x53x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x53x53x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x53x53x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x54x40x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x54x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x54x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x54x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x54x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x54x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x54x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x54x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x54x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x54x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x54x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x54x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x54x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x54x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x54x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x54x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x54x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x54x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x54x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x54x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x54x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x54x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x54x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x54x54x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x54x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x1024x54x54x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x54x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x1024x54x54x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x54x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x1024x54x54x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x54x54x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x1024x55x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x55x49x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x55x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x49x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x55x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x55x55x1x1x1x1x2048x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x55x55x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x55x55x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x55x55x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x55x55x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x55x55x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x56x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x56x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x56x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x56x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x56x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x56x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x56x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x56x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x56x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x56x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x56x50x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x56x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+8
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 16, 16, 32, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 2>+32
2x1024x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x56x56x1x1x1x1x2048x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x2048x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x56x56x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x56x56x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x1024x56x56x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x56x56x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x1024x56x56x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+16
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x1024x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x56x56x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x56x56x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x1024x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x1024x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x56x56x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x1024x56x56x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x56x56x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x1024x56x56x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x56x56x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x56x56x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x56x56x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x56x56x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x1024x56x56x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+32
2x1024x56x56x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x56x56x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x56x56x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x56x56x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x1024x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x1024x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x1024x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x57x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x57x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x57x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x57x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x57x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x57x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x57x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x57x57x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x57x57x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x57x57x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x57x57x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x1024x57x57x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x57x57x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x57x57x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x1024x57x57x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x57x57x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x57x57x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x57x57x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x1024x57x57x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x1024x57x57x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x57x57x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x57x57x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1024x57x57x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x57x57x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+64
2x1024x57x57x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x57x57x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x57x57x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x1024x57x57x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x1024x58x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x58x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x58x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x58x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x58x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x58x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x58x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x58x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x58x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x58x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x58x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x58x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x58x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x58x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x58x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x58x58x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x58x58x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x58x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x58x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x58x58x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x58x58x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x58x58x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x58x58x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x59x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x59x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x59x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x59x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x59x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x59x59x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x59x59x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x59x59x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x59x59x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x59x59x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x59x59x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x60x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x60x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x60x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x60x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x60x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x60x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x60x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x60x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x60x44x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x60x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x60x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x60x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x60x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x60x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x60x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x60x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x60x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x60x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x60x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x60x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x60x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x60x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x60x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x60x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x60x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x60x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x60x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x60x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x60x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x60x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x60x60x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x60x60x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x60x60x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x60x60x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x60x60x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x60x60x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x60x60x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x61x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x61x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x61x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x61x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x61x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x61x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x61x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x61x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x61x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x61x61x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x61x61x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x61x61x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x61x61x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x61x61x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x61x61x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x62x40x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x62x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x62x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x62x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x62x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x62x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x62x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x62x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x62x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x62x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x62x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x62x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x62x46x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x62x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x62x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x62x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x62x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x48x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x62x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x62x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x62x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x62x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x62x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x62x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x62x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x62x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x62x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x62x62x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x63x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x63x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x63x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x63x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x63x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x63x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x63x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x63x63x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x63x63x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x63x63x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x63x63x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x128x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1024x64x128x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1024x64x128x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1024x64x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x64x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x64x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x64x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x64x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x64x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x64x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x64x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x46x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x64x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x64x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x64x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x64x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x1024x64x64x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,48[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x64x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x64x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:256
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x64x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x1024x64x64x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x64x64x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x64x64x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x1024x64x64x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x64x64x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x1024x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x1024x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x64x64x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1024x64x64x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x64x64x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x64x64x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x64x64x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x64x64x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x6144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x64x64x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x64x64x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x64x64x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x64x64x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x64x64x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x64x64x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x64x64x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x1024x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x64x64x1x7x7x1x1024x4x3x3x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x65x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x65x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x65x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x65x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x65x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x65x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x65x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x65x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x65x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x66x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x66x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x66x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x66x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x66x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x66x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x66x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x66x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x44x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x66x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x66x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x66x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x66x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x66x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x66x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x66x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x66x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x66x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x66x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x66x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x66x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x66x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x66x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x66x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x66x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x66x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x66x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x66x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x66x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x66x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x67x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x67x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x67x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x67x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x67x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x67x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x67x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x67x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x67x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x67x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x68x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x68x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x68x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x68x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x68x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x68x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x68x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x68x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x68x44x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x68x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x68x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x44x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x68x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x68x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x68x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x68x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x68x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x68x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x68x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x68x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x68x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x68x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x68x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x68x50x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x68x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x1024x68x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x68x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x68x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x68x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x69x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x69x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x69x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x69x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x69x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x69x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x69x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x69x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x6x6x1x3x3x1x1024x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x6x6x1x3x3x1x1024x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x70x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x70x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x70x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x70x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x70x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x70x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x70x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x70x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x70x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x70x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x70x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x70x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x70x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x70x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x70x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x70x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x70x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x70x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x70x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x70x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x70x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x70x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x70x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x70x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x70x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x70x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x70x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x70x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x70x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x71x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x71x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x71x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x71x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x72x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x72x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x72x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x72x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x72x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x72x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x72x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x72x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x72x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x72x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x72x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x72x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x72x46x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x72x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x72x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x46x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x72x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x72x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x72x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x72x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x72x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x72x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x72x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x72x48x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x72x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x72x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x72x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x72x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x72x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x72x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x72x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x72x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x72x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x72x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x72x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x72x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x73x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x73x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x73x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x73x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x73x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x73x73x1x9x9x1x1024x1x4x4x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x74x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x74x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x74x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x74x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x74x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x74x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x74x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x74x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x74x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x74x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x74x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x74x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x74x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x74x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x74x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x74x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x74x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x74x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x74x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x74x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x74x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x74x74x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x74x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x75x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x75x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x75x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x75x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x75x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x75x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x75x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x75x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x768x768x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206
2x1024x768x768x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x768x768x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1024x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1024x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1024x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x768x768x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x1024x768x768x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2]
2x1024x768x768x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x76x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x76x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x76x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x76x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x76x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x76x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x76x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x76x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x76x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x76x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x76x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x48x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x76x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x76x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x48x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x76x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x76x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x76x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x76x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x76x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x76x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x76x50x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x76x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+2
2x1024x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x76x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x76x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x76x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1024x76x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x76x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x76x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x77x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x77x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x77x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x77x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x78x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x78x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x78x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x78x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x78x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x78x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x78x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x78x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x78x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x78x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x78x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x78x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x78x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x78x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x78x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x78x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x78x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x78x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x79x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x79x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x79x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x79x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x79x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,117;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x2051x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1024x7x7x1x1x1x1x2052x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x1024x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x1024x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x464x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x464x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x1024x7x7x1x1x1x1x464x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x464x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x464x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x464x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x464x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x464x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x1024x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x1x1x1x704x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x1x1x1x704x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x704x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x704x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x704x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x7x7x1x1x1x1x704x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x7x7x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x2x2x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,5,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x7x7x1x3x3x1x1024x4x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x7x7x1x3x3x1x1280x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x7x7x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x7x7x1x7x7x1x256x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x7x7x1x7x7x1x256x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x1024x7x7x1x7x7x1x256x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,6,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[6];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x1024x7x7x1x7x7x1x256x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x7x7x1x7x7x1x256x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x1024x7x7x1x7x7x1x256x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x7x7x1x256x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+128
2x1024x7x7x1x7x7x1x256x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x7x7x1x256x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x1024x7x7x1x7x7x1x256x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x1024x7x7x1x7x7x1x256x400x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+16
2x1024x7x7x1x7x7x1x256x400x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x1024x7x7x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x1024x7x7x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x7x7x1x7x7x1x256x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x1024x7x7x1x7x7x1x256x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x1024x7x7x1x7x7x1x256x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x1024x7x7x1x7x7x1x256x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,241[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x1024x7x7x1x7x7x1x256x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x1024x7x7x1x7x7x1x256x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[6];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x1024x7x7x1x7x7x1x256x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x80x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x80x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x80x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x80x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x80x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x80x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x80x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x80x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x80x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x80x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x80x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x80x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x80x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x80x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x80x48x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x80x48x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,4,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[4];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x80x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x80x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x80x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x80x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x80x80x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x80x80x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x80x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x81x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x81x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x82x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x82x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x82x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x82x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1024x82x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x82x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x82x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x82x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x82x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x82x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x82x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x82x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x82x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x82x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x82x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x82x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x82x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x82x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x82x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x82x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x82x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x82x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x82x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x83x39x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x83x39x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x41x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x41x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x43x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x83x43x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x45x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x83x45x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x83x47x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x49x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x83x49x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x84x40x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x84x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x84x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x84x42x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x42x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x84x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x84x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1024x84x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x84x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1024x84x44x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x84x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x84x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x84x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x84x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x84x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x84x46x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x84x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x84x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x84x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x84x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x84x48x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x84x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x84x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x84x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1024x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x84x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x84x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x84x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,316[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x8x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1024x8x8x1x7x7x1x1024x1x3x3x0x1x1x0x1x1x0x0x1024xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1024x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1024x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1024x96x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1026x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x1026x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x1030x32x32x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1030x64x64x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1040x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x1040x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x1040x32x32x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1040x64x64x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1040x64x64x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1048x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1048x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x104x128x128x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x104x128x128x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x104x128x128x1x3x3x1x104x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x104x14x14x1x1x1x1x130x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x132x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x104x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x104x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x104x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x104x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x104x14x14x1x3x3x1x104x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x104x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x256x256x1x1x1x1x208x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x104x256x256x1x1x1x1x208x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x104x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x104x28x28x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x28x28x1x3x3x1x104x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x104x512x512x1x3x3x1x104x4x1x1x0x2x2x0x1x1x0x0x13xNCHWxFP16xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x64x64x1x1x1x1x312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x104x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x104x7x7x1x1x1x1x260x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x104x7x7x1x3x3x1x104x1x1x1x0x1x1x0x1x1x0x0x104xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1056x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1056x128x128x1x1x1x1x248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x128x128x1x3x3x1x1056x4x1x1x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x128x128x1x5x5x1x1056x1x2x2x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x131x131x1x5x5x1x1056x4x0x0x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1056x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x14x14x1x1x1x1x193x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[8];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x1056x14x14x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+8
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1056x14x14x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1056x14x14x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[9];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+16
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1056x14x14x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1056x14x14x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x14x14x1x1x1x1x344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x15x15x1x3x3x1x1056x4x0x0x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x17x17x1x5x5x1x1056x4x0x0x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x256x256x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1056x256x256x1x3x3x1x1056x1x1x1x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x256x256x1x3x3x1x1056x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x28x28x1x1x1x1x2904x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x28x28x1x1x1x1x2904x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x28x28x1x3x3x1x1056x4x1x1x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x32x32x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x32x32x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x32x32x1x3x3x1x1056x1x1x1x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x33x33x1x5x5x1x1056x1x0x0x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x64x64x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x64x64x1x1x1x1x304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x64x64x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x64x64x1x3x3x1x1056x1x1x1x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x64x64x1x3x3x1x1056x4x1x1x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1056x64x64x1x5x5x1x1056x1x2x2x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1056x67x67x1x5x5x1x1056x1x0x0x0x2x2x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1056x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1056x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1056x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1056x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1056x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1056x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1056x7x7x1x3x3x1x1056x1x1x1x0x1x1x0x1x1x0x0x1056xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x105x1x1x1x1x1x1x1260x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x105x1x1x1x1x1x1x1266x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x106x14x14x1x1x1x1x636x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x106x1x1x1x1x1x1x1272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x106x1x1x1x1x1x1x2544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x106x64x64x1x1x1x1x636x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1072x14x14x1x1x1x1x704x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1072x14x14x1x1x1x1x704x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1072x56x56x1x1x1x1x704x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x1072x56x56x1x1x1x1x704x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1076x128x128x1x1x1x1x90x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x1076x128x128x1x5x5x1x1076x1x2x2x0x2x2x0x1x1x0x0x1076xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1076x14x14x1x1x1x1x90x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1076x14x14x1x5x5x1x1076x4x2x2x0x2x2x0x1x1x0x0x1076xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1076x1x1x1x1x1x1x268x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1076x1x1x1x1x1x1x268x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1076x64x64x1x1x1x1x90x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x1076x64x64x1x5x1x1x1076x1x2x0x0x1x1x0x1x1x0x0x1076xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1076x7x7x1x1x5x1x1076x1x0x2x0x1x1x0x1x1x0x0x1076xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1080x256x256x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1080x28x28x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x128x128x1x3x3x1x1088x4x1x1x0x2x2x0x1x1x0x0x17xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1088x12x12x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x12x12x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x12x12x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1088x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1088x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1088x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1088x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x14x14x1x3x3x1x1088x1x1x1x0x2x2x0x1x1x0x0x17xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x1x1x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x1x1x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x256x256x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1088x28x28x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x32x32x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x62x62x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1088x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1088x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1088x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1088x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1088x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1088x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1088x7x7x1x3x3x1x1088x1x1x1x0x1x1x0x1x1x0x0x17xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x108x128x128x1x1x1x1x108x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x108x1x1x1x1x1x1x1302x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x108x1x1x1x1x1x1x436x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x108x256x256x1x3x3x1x108x4x1x1x0x1x1x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x108x256x256x1x7x7x1x108x1x3x3x0x1x1x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x108x28x28x1x1x1x1x108x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x108x28x28x1x3x3x1x108x1x1x1x0x1x1x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x108x28x28x1x5x5x1x108x4x2x2x0x1x1x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x108x56x56x1x1x1x1x108x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x108x57x57x1x3x3x1x108x1x0x0x0x2x2x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x108x61x61x1x7x7x1x108x1x0x0x0x2x2x0x1x1x0x0x108xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x108x64x64x1x1x1x1x648x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1092x32x32x1x1x1x1x196x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1092x7x7x1x1x1x1x196x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1096x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1096x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1096x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1098x128x128x1x3x3x1x1098x1x1x1x0x2x2x0x1x1x0x0x1098xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1098x1x1x1x1x1x1x91x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1098x64x64x1x1x1x1x217x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x109x128x128x1x1x1x1x654x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x109x64x64x1x1x1x1x654x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x10x1024x1024x1x3x3x1x10x1x1x1x0x1x1x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x10x1x1x1x1x1x1x175x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x175x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x51x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x51x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x61x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x256x256x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x256x256x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x32x32x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x512x512x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x512x512x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x10x512x512x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x10x512x512x1x1x1x1x5x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x512x512x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x10x56x56x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x56x56x1x1x1x1x20x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x56x56x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x10x56x56x1x7x7x1x10x1x3x3x0x1x1x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x10x64x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x10x64x64x1x3x3x1x10x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1104x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1104x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1104x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1104x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x32x32x1x5x5x1x1104x1x2x2x0x1x1x0x1x1x0x0x1104xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1104x64x64x1x1x1x1x184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x64x64x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x64x64x1x5x5x1x1104x1x2x2x0x1x1x0x1x1x0x0x1104xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1104x7x7x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1104x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1104x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1104x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1104x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1104x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1104x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1104x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1104x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1104x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1104x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x11110x128x128x1x1x1x1x28280x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x11110x128x128x1x3x3x1x11110x1x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x11110x128x128x1x3x3x1x11110x4x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x11110x14x14x1x1x1x1x11110x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x11110x14x14x1x1x1x1x28280x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x11110x256x256x1x3x3x1x11110x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x11110x28x28x1x3x3x1x11110x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x11110x64x64x1x1x1x1x11110x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x11110x64x64x1x1x1x1x28280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1120x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1120x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1120x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1120x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1120x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1120x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1120x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1120x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1120x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1120x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1120x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1120x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1120x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1120x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1120x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1120x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1120x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1120x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1120x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1120x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x11264x64x64x1x1x1x1x2816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,77[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x1024x1024x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x112x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x112x112x112x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x128x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x112x128x128x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x112x128x128x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x112x128x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x128x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x128x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x112x128x128x1x3x3x1x112x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x112x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x112x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x112x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x112x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x112x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x112x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x112x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x112x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x112x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[7];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x112x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x112x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x112x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x112x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x112x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x112x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x112x14x14x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x220x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x14x14x1x3x3x1x224x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x112x14x14x1x3x3x1x224x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x112x14x14x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x14x14x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x14x14x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x112x14x14x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x112x14x14x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x112x14x14x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x112x14x14x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x112x14x14x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x112x14x14x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x112x14x14x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x112x14x14x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x14x14x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x112x14x14x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x112x14x14x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x112x14x14x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x14x14x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x112x14x14x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x112x14x14x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x112x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x112x15x15x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x112x1x1x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x112x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[9];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[9];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x112x256x256x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x112x256x256x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x112x256x256x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x256x256x1x3x3x1x112x4x1x1x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x256x256x1x3x3x1x112x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x257x257x1x3x3x1x112x1x0x0x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x259x259x1x5x5x1x112x1x0x0x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x28x28x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x28x28x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x112x28x28x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x28x28x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x28x28x1x5x5x1x112x1x2x2x0x2x2x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x112x32x32x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x112x32x32x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x112x32x32x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x32x32x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x112x32x32x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x32x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x112x32x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x112x32x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x112x32x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x112x32x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x112x32x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x112x34x34x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x112x512x512x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x112x512x512x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x512x512x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x512x512x1x3x3x1x112x4x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x56x56x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x112x56x56x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x112x56x56x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x112x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x112x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x112x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x112x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x112x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x112x64x128x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x112x64x128x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x112x64x128x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x112x64x64x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x112x64x64x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x112x64x64x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x112x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1130x32x32x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1130x7x7x1x5x5x1x1130x4x2x2x0x1x1x0x1x1x0x0x1130xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x113x1x1x1x1x1x1x1356x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1144x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1148x64x64x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1148x64x64x1x5x5x1x1148x1x2x2x0x1x1x0x1x1x0x0x1148xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1148x7x7x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x128x128x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1152x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1152x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1152x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x128x128x1x3x3x1x1152x1x1x1x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x128x128x1x5x5x1x1152x1x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x128x128x1x5x5x1x1152x4x2x2x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x131x131x1x5x5x1x1152x1x0x0x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1152x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x14x14x1x3x3x1x1152x1x1x1x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1152x14x14x1x3x3x1x1152x4x1x1x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x14x14x1x5x5x1x1152x1x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x14x14x1x5x5x1x1152x4x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1152x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1152x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1152x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x1152x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x1152x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x1152x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1152x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x1152x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1152x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1152x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1152x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1152x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1152x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1152x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1152x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1152x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1152x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1152x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1152x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1152x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1152x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x1x1x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1152x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x28x28x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x32x32x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1152x32x32x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x32x32x1x3x3x1x1152x1x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x32x32x1x3x3x1x1152x1x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1152x32x32x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x32x32x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x32x32x1x3x3x1x768x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x64x64x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x64x64x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x64x64x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x64x64x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1152x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1152x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1152x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1152x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,185[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1152x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1152x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1152x7x7x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x16x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x1152x7x7x1x3x3x1x1152x1x1x1x0x2x2x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x32x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1152x7x7x1x3x3x1x1152x4x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1152x7x7x1x3x3x1x1152x64x1x1x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1152x7x7x1x5x5x1x1152x16x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x5x5x1x1152x32x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1152x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1158x128x128x1x3x3x1x1158x4x1x1x0x2x2x0x1x1x0x0x1158xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1158x32x32x1x1x1x1x210x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1158x64x64x1x3x3x1x1158x1x1x1x0x2x2x0x1x1x0x0x1158xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1158x7x7x1x1x1x1x210x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1160x1x1x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1160x32x32x1x5x5x1x1160x1x2x2x0x1x1x0x1x1x0x0x1160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1160x64x64x1x5x5x1x1160x1x2x2x0x1x1x0x1x1x0x0x1160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1168x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x112x112x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x112x112x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x113x113x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x113x113x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x128x128x1x1x1x1x315x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x116x128x128x1x1x1x1x354x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x116x128x128x1x1x5x1x116x1x0x2x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x13x13x1x3x3x1x116x1024x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x13x13x1x3x3x1x116x1024x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x116x13x13x1x3x3x1x116x512x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x13x13x1x3x3x1x116x512x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x116x14x14x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x116x14x14x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x14x14x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x116x14x14x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x14x14x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x116x14x14x1x1x1x1x719x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x1024x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x1024x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x1024x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x116x14x14x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x16x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x32x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x116x14x14x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x116x14x14x1x3x3x1x116x512x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x512x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x512x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x116x14x14x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x14x14x1x3x3x1x116x64x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+64
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+64
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x116x15x15x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x15x15x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x116x15x15x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x15x15x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x116x256x256x1x1x5x1x116x1x0x2x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x27x27x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x27x27x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x116x28x28x1x1x1x1x116x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x28x28x1x1x1x1x116x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x116x28x28x1x3x3x1x116x1024x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x16x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x32x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x512x0x0x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x28x28x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x28x28x1x5x1x1x116x1x2x0x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x116x28x28x1x5x1x1x116x4x2x0x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x116x29x29x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x29x29x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x116x512x512x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x116x56x56x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x56x56x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x57x57x1x3x3x1x116x1024x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x116x57x57x1x3x3x1x116x512x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1176x32x32x1x1x1x1x211x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1176x32x32x1x3x3x1x1176x1x1x1x0x1x1x0x1x1x0x0x1176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1176x64x64x1x1x1x1x211x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1176x7x7x1x3x3x1x1176x4x1x1x0x1x1x0x1x1x0x0x1176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x117x128x128x1x1x1x1x702x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x117x14x14x1x1x1x1x702x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x117x1x1x1x1x1x1x1404x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1184x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1184x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1184x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1184x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1184x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1184x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1184x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1184x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1184x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1184x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1184x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1192x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1192x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x119x128x128x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x119x128x128x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x119x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x11x225x225x1x1x1x1x11x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1200x128x128x1x5x5x1x1200x1x2x2x0x1x1x0x1x1x0x0x1200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1200x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1200x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1200x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1200x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1200x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1200x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x17x17x1x5x5x1x1200x1x0x0x0x2x2x0x1x1x0x0x1200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1200x1x1x1x1x1x1x100x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x33x33x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x64x64x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x64x64x1x1x1x1x344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1200x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1200x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1200x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1200x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1200x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1200x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1200x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1200x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1200x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1200x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1200x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x128x128x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x128x128x1x1x1x1x217x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x128x128x1x1x1x1x226x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x128x128x1x1x1x1x235x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x128x128x1x1x1x1x304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x1x1x1x30x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x128x128x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x1x1x1x340x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x128x128x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x128x128x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x128x128x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x128x128x1x5x1x1x120x4x2x0x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x128x128x1x5x5x1x120x1x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x128x128x1x5x5x1x120x4x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x13x13x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x13x13x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x13x13x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x13x13x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x13x13x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x13x13x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x13x13x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x13x13x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x13x13x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x13x13x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x13x13x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x360x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x120x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x120x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x802x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x14x14x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x120x14x14x1x3x3x1x120x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x120x14x14x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x14x14x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x14x14x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x14x14x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x14x14x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x14x14x1x3x3x1x120x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x14x14x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x14x14x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x14x14x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x120x14x14x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x3x3x1x120x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x14x14x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x14x14x1x5x5x1x120x1x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x14x14x1x7x7x1x120x4x3x3x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x15x15x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x15x15x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x15x15x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x15x15x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x15x15x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x15x15x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x16x16x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x16x16x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x17x17x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x1x1x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x1x1x1x1x1x1x2880x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x1x1x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x24x24x1x5x5x1x120x4x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x256x256x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x256x256x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x256x256x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x256x256x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x120x256x256x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x256x256x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x256x256x1x3x3x1x85x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x336x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x120x28x28x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x120x28x28x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x120x28x28x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x28x28x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x28x28x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x28x28x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x120x28x28x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x28x28x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x3x3x1x120x4x1x1x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x120x28x28x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x120x28x28x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x28x28x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x28x28x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x28x28x1x3x3x1x85x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x28x28x1x3x3x1x85x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x16x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x120x28x28x1x5x5x1x120x1x2x2x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x32x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x28x28x1x5x5x1x120x64x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x120x28x28x1x7x7x1x120x1x3x3x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x29x29x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x120x29x29x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x120x29x29x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x29x29x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x29x29x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x120x29x29x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x29x29x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x29x29x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x120x29x29x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x29x29x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x29x29x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x29x29x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x120x29x29x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x120x29x29x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x29x29x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x29x29x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x32x32x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x512x512x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x512x512x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x55x55x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x55x55x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x55x55x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x55x55x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x55x55x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x56x56x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x56x56x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x56x56x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x56x56x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x56x56x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x56x56x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x56x56x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x56x56x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x56x56x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x56x56x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x56x56x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x5xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x56x56x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x56x56x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x120x56x56x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x120x57x57x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x57x57x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x57x57x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x57x57x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x57x57x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x120x64x64x1x1x1x1x30x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x64x64x1x1x1x1x360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x64x64x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x64x64x1x3x3x1x240x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x120x6x6x1x3x3x1x120x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x6x6x1x3x3x1x120x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x6x6x1x3x3x1x120x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x6x6x1x3x3x1x120x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x6x6x1x3x3x1x120x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x6x6x1x3x3x1x120x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x7x7x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x7x7x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x7x7x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x7x7x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x120x7x7x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x120x7x7x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x120x7x7x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x7x7x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x7x7x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x7x7x1x7x7x1x120x1x3x3x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x120x8x8x1x3x3x1x120x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x120x8x8x1x3x3x1x120x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x8x8x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x120x8x8x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x8x8x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x120x8x8x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x8x8x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x120x8x8x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x120x8x8x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1216x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x128x128x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x128x128x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1216x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1216x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1216x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1216x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1216x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1216x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1216x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1216x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1216x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1216x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1216x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1216x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1216x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1216x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1216x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1216x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1216x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x12288x128x128x1x3x3x1x12288x4x1x1x0x2x2x0x1x1x0x0x12288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x12288x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,77[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x12288x64x64x1x3x3x1x12288x1x1x1x0x2x2x0x1x1x0x0x12288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x12288x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1228x32x32x1x5x5x1x1228x1x2x2x0x1x1x0x1x1x0x0x1228xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1228x64x64x1x5x5x1x1228x4x2x2x0x1x1x0x1x1x0x0x1228xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x122x128x128x1x1x1x1x732x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x122x128x128x1x3x3x1x78x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x122x256x256x1x1x1x1x732x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x122x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x122x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x122x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x122x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+32
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+32
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x122x28x28x1x3x3x1x122x16x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+16
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+16
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+64
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+64
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x122x28x28x1x3x3x1x122x64x1x1x0x1x1x0x1x1x0x0x122xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+32
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+32
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x28x28x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x122x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x122x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x122x56x56x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x122x56x56x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x122x56x56x1x3x3x1x122x16x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x122x56x56x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x122x56x56x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x122x56x56x1x3x3x1x122x64x1x1x0x2x2x0x1x1x0x0x122xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x1232x128x128x1x3x3x1x1232x4x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1232x14x14x1x1x1x1x1232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1232x14x14x1x1x1x1x3024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1232x14x14x1x3x3x1x1232x1x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1232x14x14x1x3x3x1x1232x4x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1232x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1232x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1232x1x1x1x1x1x1x308x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1232x256x256x1x3x3x1x1232x1x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1232x256x256x1x3x3x1x1232x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1232x28x28x1x3x3x1x1232x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1232x64x64x1x1x1x1x3024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x123x128x128x1x1x1x1x738x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x123x128x128x1x1x1x1x738x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1240x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1240x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1240x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1240x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1248x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x16x16x1x1x5x1x1248x1x0x2x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1248x16x16x1x5x1x1x1248x1x2x0x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1248x1x1x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x1x1x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x32x32x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x32x32x1x5x1x1x1248x1x2x0x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1248x32x32x1x5x1x1x1248x4x2x0x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1248x3x3x1x5x1x1x1248x1x2x0x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1248x3x3x1x5x1x1x1248x4x2x0x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1248x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x64x64x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x64x64x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1248x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1248x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1248x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1248x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1248x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1248x7x7x1x3x3x1x1248x1x1x1x0x1x1x0x1x1x0x0x1248xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1248x9x9x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x124x128x128x1x1x1x1x372x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x124x128x128x1x3x3x1x124x4x1x1x0x1x1x0x1x1x0x0x124xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x124x14x14x1x1x1x1x372x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x124x32x32x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x125x128x128x1x1x1x1x750x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x125x14x14x1x1x1x1x750x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x125x1x1x1x1x1x1x1500x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x125x256x256x1x3x3x1x87x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x125x256x256x1x3x3x1x87x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1260x32x32x1x3x3x1x1260x1x1x1x0x1x1x0x1x1x0x0x1260xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1260x7x7x1x1x1x1x226x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1264x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1264x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1266x1x1x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1266x32x32x1x1x1x1x226x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1266x32x32x1x5x5x1x1266x1x2x2x0x1x1x0x1x1x0x0x1266xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1266x7x7x1x1x1x1x226x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1266x7x7x1x3x3x1x1266x1x1x1x0x1x1x0x1x1x0x0x1266xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x126x128x128x1x1x1x1x818x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x126x56x56x1x1x1x1x35x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x126x64x64x1x1x1x1x818x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1272x64x64x1x1x1x1x234x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x10x10x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x10x10x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x128x128x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x128x128x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x1280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1280x128x128x1x3x3x1x1280x1x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x1280x12x12x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x1280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1280x14x14x1x3x3x1x2560x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x16x16x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x16x16x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x16x16x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x16x16x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x16x16x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x16x16x1x1x1x1x640x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x16x16x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1280x16x16x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x1280x16x16x1x1x1x1x640x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4;TransposedConvBinWinoRxS<3-2>:189
2x1280x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1;TransposedConvBinWinoRxS<2-3>:236;TransposedConvBinWinoRxS<3-2>:204
2x1280x16x16x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x3x3x1x1280x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x1280x280x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:131
2x1280x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x16x16x1x3x3x1x1280x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x16x16x1x3x3x1x1280x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x1280x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x16x16x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x16x16x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x16x16x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1280x16x16x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x16x16x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1280x16x16x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x16x16x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x1280x16x16x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,60;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x16x16x1x3x3x1x640x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x16x16x1x3x3x1x640x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x16x16x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1280x16x16x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x16x16x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1280x16x16x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x16x16x1x3x3x1x640x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x1x3000x1x1x3x1x1280x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x1x3000x1x1x3x1x1280x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x20x20x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x22x22x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1280x24x24x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x24x24x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x24x24x1x3x3x1x1280x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x2x2x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x32x32x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x32x32x1x1x1x1x2176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x1x1x1x320x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x32x32x1x1x1x1x320x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1280x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:190
2x1280x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x1280x32x32x1x3x3x1x1280x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x640x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x640x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:200
2x1280x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x40x40x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x48x48x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x48x48x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x4x4x1x1x1x1x1280x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:185
2x1280x4x4x1x1x1x1x1280x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:45
2x1280x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:40
2x1280x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:46
2x1280x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:229;TransposedConvBinWinoRxS<3-2>:248
2x1280x4x4x1x1x1x1x2560x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x4x4x1x1x1x1x2560x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x4x4x1x1x1x1x3840x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x1280x4x4x1x1x1x1x3840x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:147
2x1280x4x4x1x1x1x1x3840x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1280x4x4x1x1x1x1x3840x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x1280x4x4x1x1x1x1x3840x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:128
2x1280x4x4x1x3x3x1x1280x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x4x4x1x3x3x1x1280x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x4x4x1x3x3x1x1280x30x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:231
2x1280x4x4x1x3x3x1x1280x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x4x4x1x3x3x1x1280x6x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:42
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,10;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:40
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:42
2x1280x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:230
2x1280x4x4x1x3x3x1x1280x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x4x4x1x3x3x1x2560x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x1280x4x4x1x3x3x1x2560x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1280x5x5x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x5x5x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x5x5x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x5x5x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x62x62x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x62x62x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x62x62x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x64x64x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x64x64x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x64x64x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x64x64x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x6x6x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x6x6x1x3x3x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x6x6x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x6x6x1x3x3x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1280x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x1280x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x1280x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x1280x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1280x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x1280x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+8
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1280x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x1280x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x1280x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x7x7x1x1x1x1x7680x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1280x7x7x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x7x7x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1280x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x1280x8x8x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x8x8x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x8x8x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x8x8x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x1280x8x8x1x1x1x1x2560x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x1280x8x8x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1280x8x8x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x320x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x384x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1280x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1280x8x8x1x1x1x1x448x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x1280x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x8x8x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:54
2x1280x8x8x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1280x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x8x8x1x3x3x1x1280x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1280x8x8x1x3x3x1x1280x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x8x8x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+2
2x1280x8x8x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1280x8x8x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x1280x8x8x1x3x3x1x2560x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1280x8x8x1x3x3x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1280x8x8x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1288x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1288x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x100x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x100x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x100x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x100x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x100x136x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x100x136x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x136x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x136x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x136x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x100x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x136x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x136x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x100x136x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x100x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x100x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x100x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x100x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x152x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x152x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x100x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x100x152x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x100x152x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x152x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x152x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x152x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x100x152x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x100x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x100x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x100x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x100x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x100x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x100x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x100x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x100x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x100x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x100x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x100x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x100x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x100x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x100x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x100x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x100x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x100x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x100x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x100x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x100x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x100x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x100x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x100x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x100x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x100x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x100x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x100x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x1024x1024x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x128x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x128x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x128x1024x1024x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x1024x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[9];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+32
2x128x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1]
2x128x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x103x103x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x103x103x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x103x103x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x103x103x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x104x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x104x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x104x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x104x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x104x104x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x104x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x104x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x104x104x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x104x104x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x104x104x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x104x104x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x104x104x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x104x104x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x104x104x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x104x104x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x104x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x104x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x104x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x104x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x104x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x104x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x104x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x104x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x104x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x104x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x104x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x104x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x104x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x104x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x104x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x104x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x104x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x104x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x104x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x104x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x104x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x104x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x104x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x104x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x104x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x104x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x104x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x104x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x104x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x104x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x104x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x104x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x105x105x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x105x105x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x105x105x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x105x105x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x105x105x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8]
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x105x105x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x108x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x108x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x108x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x108x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x108x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x108x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x108x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x108x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x108x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x108x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x108x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x108x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x108x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x108x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x108x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x108x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x108x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x108x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x108x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x108x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x108x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x108x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x108x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x108x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x108x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x108x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x108x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x108x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x108x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x108x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x108x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x108x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x108x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x108x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x108x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x108x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:239
2x128x10x10x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:103
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:239
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:94;TransposedConvBinWinoRxS<3-2>:87
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:238
2x128x10x10x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:72
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:251
2x128x10x10x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:71
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:64
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;TransposedConvBinWinoRxS<3-2>:199
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:80
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;TransposedConvBinWinoRxS<3-2>:214
2x128x10x10x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];TransposedConvBinWinoRxS<2-3>:85;TransposedConvBinWinoRxS<3-2>:81
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:70
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,3,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];TransposedConvBinWinoRxS<3-2>:20
2x128x10x10x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[9];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:64
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:68
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];TransposedConvBinWinoRxS<3-2>:35
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];TransposedConvBinWinoRxS<2-3>:75;TransposedConvBinWinoRxS<3-2>:67
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];TransposedConvBinWinoRxS<3-2>:34
2x128x10x10x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:68
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];TransposedConvBinWinoRxS<3-2>:41
2x128x10x10x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:70
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:252
2x128x10x10x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:77;TransposedConvBinWinoRxS<3-2>:79
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:255
2x128x10x10x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:109;TransposedConvBinWinoRxS<3-2>:64
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:74
2x128x10x10x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:140
2x128x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:122
2x128x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:132
2x128x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:42
2x128x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x10x10x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:33
2x128x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x10x10x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:13
2x128x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x128x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x10x10x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:67
2x128x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x10x10x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x10x10x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:70
2x128x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x10x10x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x10x10x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x128x10x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x10x15x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x10x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x111x111x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x111x111x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x111x111x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x112x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x112x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x112x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x112x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x112x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x112x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x128x112x112x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x128x112x112x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x128x112x112x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[1]
2x128x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x128x112x112x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[1]
2x128x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[1]
2x128x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3]
2x128x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6]
2x128x112x112x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x112x112x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x112x112x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x112x112x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x112x112x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:16
2x128x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x112x112x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x128x112x112x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x112x112x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x128x112x112x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x128x112x112x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x112x112x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x112x112x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x112x112x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x128x112x112x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x112x112x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x112x112x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x112x112x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x112x112x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x128x112x112x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,79[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x112x112x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x112x112x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x112x112x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x128x112x112x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x112x112x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x112x112x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x112x112x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x112x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x112x112x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x112x112x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x112x112x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x128x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:48
2x128x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x128x112x112x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x128x112x112x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x112x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:185
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x112x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x112x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x112x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x112x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x112x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x112x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x112x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x112x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x112x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x112x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x112x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x112x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x112x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x112x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x112x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x112x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x112x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x112x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x112x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x112x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x113x113x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x128x113x113x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x113x113x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x113x113x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x113x113x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x113x113x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x128x113x113x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x113x113x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x113x113x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x128x113x113x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x113x113x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,170[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x113x113x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x113x113x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x113x113x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x113x113x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,79[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x113x113x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x113x113x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x113x113x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x113x113x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x113x113x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8]
2x128x113x113x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x113x113x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x113x113x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x113x113x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x113x113x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x113x113x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x113x113x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x113x113x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x113x113x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:95
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x113x113x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,172[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x114x114x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x128x114x114x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x114x114x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x114x114x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x114x114x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,170[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,170[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x128x114x114x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,170[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x114x114x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3]
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x114x114x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x114x114x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x114x114x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x114x114x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x115x115x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x115x115x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x115x115x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x115x115x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x115x115x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x115x115x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x115x115x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x115x115x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x115x115x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x115x115x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x116x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x116x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x116x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x116x116x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x116x116x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x116x116x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x116x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x116x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x116x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x116x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x116x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x116x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x116x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x116x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x116x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x116x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x116x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x116x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x116x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x116x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x116x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x116x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x116x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x116x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x116x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x116x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x116x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x116x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x116x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x1184x1184x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x118x118x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x118x118x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x118x118x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x11x11x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x128x11x11x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x11x11x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x11x11x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x11x11x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x11x11x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x120x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x120x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x120x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x120x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x120x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x120x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x120x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x120x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x120x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x120x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x120x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x120x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x120x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x120x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x120x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x120x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x120x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x120x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x120x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x120x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x120x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x120x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x120x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x120x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x120x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x120x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x120x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x120x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x120x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x120x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x120x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x120x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x120x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x120x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x124x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x124x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x124x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x124x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x124x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x124x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x124x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x124x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x124x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x124x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x124x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x124x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x124x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x124x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x124x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x124x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x124x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x124x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x124x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x124x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x124x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x124x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x124x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x124x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x124x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x124x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x124x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x124x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x124x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x124x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x124x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x124x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x124x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x124x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x124x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x124x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x126x126x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x128x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x128x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x128x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x1x1x1x180x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4]
2x128x128x128x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x128x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[1]
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x128x128x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3]
2x128x128x128x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x128x128x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x128x128x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x128x128x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67
2x128x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x128x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1]
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x128x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x128x128x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x128x128x1x3x3x1x128x140x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x128x128x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x128x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x128x128x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x128x128x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x128x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x128x128x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x128x128x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x128x128x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x128x1x4x4x1x128x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x128x128x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x128x128x1x7x7x1x128x1x9x9x0x1x1x0x3x3x0x0x128xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x128x256x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x256x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x128x256x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x256x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x128x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x128x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x128x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x128x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x128x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x128x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x128x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x128x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x128x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x128x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x128x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x128x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x128x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x128x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x128x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x128x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x128x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x128x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x128x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x128x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x128x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x128x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x12x12x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x12x12x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x12x12x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x12x12x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x12x12x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x132x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x132x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x132x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x132x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x132x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x132x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x132x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x132x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x132x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x132x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x132x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x132x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x132x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x132x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x132x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x132x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x132x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x132x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x132x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x132x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x132x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x132x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x132x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x132x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x132x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x132x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x132x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x132x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x132x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x132x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x132x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x136x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x136x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x136x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x136x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x136x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x136x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x136x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x136x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x136x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x136x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x136x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x136x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x136x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x136x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x136x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x136x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x136x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x136x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x136x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x136x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x136x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x136x88x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x136x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x136x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x136x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x136x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x136x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x136x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x136x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x136x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x136x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x136x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x136x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x13x13x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x13x13x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x13x13x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x13x13x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x128x13x25x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x13x25x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x140x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x140x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x140x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x140x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x140x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x140x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x140x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x140x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x140x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x140x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x140x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x140x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x140x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x140x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x140x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x140x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x140x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x140x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x140x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x140x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x140x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x140x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x140x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x140x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x140x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x140x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x144x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x144x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x144x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x144x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x144x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x144x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x144x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x144x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x144x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x144x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x144x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x144x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x144x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x144x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x144x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x144x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x144x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x144x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x144x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x144x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x144x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x144x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x144x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x144x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x144x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x144x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x144x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x144x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x144x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x144x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x144x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x144x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x144x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x147x147x1x4x4x1x128x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x148x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x148x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x148x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x148x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x148x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x148x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x148x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x148x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x148x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x148x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x148x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x148x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x148x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x148x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x148x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x148x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x148x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x148x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x148x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x148x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x148x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x148x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x148x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x148x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x148x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x148x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x148x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+2
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x148x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x148x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[9];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[8];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[10];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+64
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[7];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,81[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x128x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,83[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x14x14x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x14x14x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x128x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x14x14x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x3x3x1x528x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x14x14x1x3x3x1x528x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+-1
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x128x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2
2x128x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:18
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x128x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x14x14x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x14x14x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x14x14x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:14
2x128x14x14x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x14x14x1x7x7x1x128x4x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x152x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x152x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x152x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x152x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x152x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x152x100x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x152x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x152x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x152x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x152x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x152x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x152x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x152x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x152x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x152x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x152x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x152x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x152x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x152x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x152x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x152x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x152x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x152x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x152x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x152x96x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x152x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x152x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x152x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x128x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x128x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1]
2x128x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x156x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x156x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x156x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x156x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x156x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x156x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x156x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x156x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x156x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x156x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x156x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x156x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x156x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x156x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x156x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x156x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x156x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x156x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x15x15x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x15x15x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x128x15x21x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x15x21x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x15x21x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x160x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x160x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x160x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x160x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x160x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x160x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x160x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x160x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x160x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x160x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x160x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x160x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x160x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x160x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x160x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x160x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x160x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x160x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x160x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x160x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x160x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x160x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x160x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x160x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x160x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x160x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x160x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x164x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x164x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x164x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x164x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x164x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x164x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x164x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x164x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x164x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x164x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x164x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x164x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x164x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x164x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x164x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x164x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x164x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x164x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x164x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x164x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x164x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x164x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x164x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x164x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x164x92x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x164x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x164x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x164x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x164x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x164x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x168x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x168x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x168x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x168x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x168x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x168x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x168x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x168x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x168x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x168x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x168x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x168x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x168x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x168x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x168x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x168x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x168x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x168x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x168x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x168x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x168x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x168x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x168x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x168x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x168x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x168x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x168x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x168x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x168x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x168x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x168x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x168x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x16x16x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x16x16x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x16x16x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x16x16x1x3x3x1x256x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x16x16x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x16x16x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x16x16x1x3x3x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x16x16x1x3x3x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x16x16x1x4x4x1x128x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x16x16x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x16x16x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x16x16x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x16x16x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x16x16x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x16x16x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x16x16x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x16x16x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x16x16x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x17x17x1x1x7x1x128x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x1x7x1x128x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x17x17x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x128x17x17x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x17x17x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x17x17x1x7x1x1x128x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x7x1x1x128x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x18x18x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x18x18x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x18x18x1x3x3x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x18x18x1x3x3x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x18x18x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x18x18x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x18x18x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x192x192x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x192x192x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x192x192x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x1x1x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,102[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x1542x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1x1x1x1x1x1x64x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x1x1x1x1x1x1x64x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x1x1x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x2048x2048x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x2048x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x2048x2048x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x128x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x128x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x128x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10]
2x128x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1]
2x128x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x128x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x205x205x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x207x207x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2]
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x207x207x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x209x209x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x209x209x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x209x209x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x209x209x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x209x209x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x209x209x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x209x209x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x209x209x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x209x209x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x209x209x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x209x209x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x209x209x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x20x30x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x20x30x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x20x30x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x20x30x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x20x30x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x20x30x1x3x3x1x384x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x20x30x1x3x3x1x384x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x384x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x20x30x1x3x3x1x384x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x20x30x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x20x30x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x20x30x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x20x30x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x20x30x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x218x218x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x128x218x218x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x128x218x218x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+8
2x128x21x15x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,60[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x21x15x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x21x15x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x21x15x1x3x3x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x220x220x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x220x220x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x128x220x220x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+8
2x128x222x222x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x222x222x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x128x222x222x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x223x223x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x223x223x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x223x223x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x223x223x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x224x224x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x224x224x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x224x224x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x224x224x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x224x224x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x224x224x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x224x224x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x224x224x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x224x224x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x224x224x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x224x224x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x224x224x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x225x225x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x225x225x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x225x225x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x225x225x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x225x225x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x225x225x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x225x225x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x227x227x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x227x227x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x227x227x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x228x228x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x228x228x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x228x228x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x228x228x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x228x228x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x228x228x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x228x228x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x229x229x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x229x229x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x229x229x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x229x229x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x229x229x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x2368x2368x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x24x16x1x2x2x1x128x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x24x16x1x2x2x1x128x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x24x16x1x2x2x1x128x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x24x16x1x2x2x1x128x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x128x24x16x1x2x2x1x128x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x24x16x1x2x2x1x128x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x24x16x1x2x2x1x128x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x24x16x1x2x2x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x24x16x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x24x16x1x2x2x1x128x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x24x16x1x2x2x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x128x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x24x16x1x2x2x1x128x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x24x16x1x2x2x1x192x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x24x16x1x2x2x1x192x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x16x1x2x2x1x192x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x16x1x2x2x1x192x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x24x24x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x24x24x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x24x24x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x24x24x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x24x24x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x128x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x256x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x256x256x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x256x256x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x256x256x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x256x256x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x256x256x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x256x256x1x5x5x1x128x1x2x2x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x256x256x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x256x256x1x7x7x1x256x1x3x3x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x25x13x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x25x13x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x26x26x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x26x26x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x26x26x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x128x26x26x1x3x3x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,171;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,45[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x27x27x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x27x27x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x27x27x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x27x27x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x27x27x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x27x27x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x27x27x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x27x27x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x27x27x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x27x27x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x27x27x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x27x27x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x27x27x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x27x27x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x27x27x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x11x11x1x128x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[8];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2]
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+64
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x352x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,187[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+64
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x28x28x1x1x1x1x416x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x416x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,175[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,83[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x128x28x28x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:130
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:70
2x128x28x28x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:254
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:67;TransposedConvBinWinoRxS<3-2>:92
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:251
2x128x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:69
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:205
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:215
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:89
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];TransposedConvBinWinoRxS<2-3>:69;TransposedConvBinWinoRxS<3-2>:64
2x128x28x28x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:64
2x128x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:93
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:247
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:66
2x128x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:72
2x128x28x28x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:69
2x128x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:95
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:92;TransposedConvBinWinoRxS<3-2>:76
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:80;TransposedConvBinWinoRxS<3-2>:65
2x128x28x28x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:67;TransposedConvBinWinoRxS<3-2>:81
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:254
2x128x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:72
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:68
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;TransposedConvBinWinoRxS<3-2>:246
2x128x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:74
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,83[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:65
2x128x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:67
2x128x28x28x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:82
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:68
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x128x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:65
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:83;TransposedConvBinWinoRxS<3-2>:82
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:66
2x128x28x28x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:214
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:208
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:83;TransposedConvBinWinoRxS<3-2>:76
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:76;TransposedConvBinWinoRxS<3-2>:68
2x128x28x28x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x128x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x5x1x512x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x2x2x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:17
2x128x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:24
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:251
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:86
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:239
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:234
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:76;TransposedConvBinWinoRxS<3-2>:66
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:243
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:203
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:91;TransposedConvBinWinoRxS<3-2>:21
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:216
2x128x28x28x1x3x3x1x128x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:204
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:188
2x128x28x28x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:203
2x128x28x28x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:200
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:207
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:212
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:207
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:139;TransposedConvBinWinoRxS<3-2>:21
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:206
2x128x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];TransposedConvBinWinoRxS<2-3>:78;TransposedConvBinWinoRxS<3-2>:31
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x28x28x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:242
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:240
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:242
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:98
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:241
2x128x28x28x1x3x3x1x128x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78
2x128x28x28x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:243
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:249
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:61
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:249
2x128x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];TransposedConvBinWinoRxS<2-3>:70;TransposedConvBinWinoRxS<3-2>:17
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:255
2x128x28x28x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:239
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:97;TransposedConvBinWinoRxS<3-2>:48
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];TransposedConvBinWinoRxS<3-2>:248
2x128x28x28x1x3x3x1x128x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:251
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:221
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:200
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:201
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:208
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:218
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:23
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:234
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:32
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:223
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:37
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:239
2x128x28x28x1x3x3x1x128x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:27
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:231
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:226
2x128x28x28x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:243
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:118
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:253
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:81;TransposedConvBinWinoRxS<3-2>:17
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:61
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:234
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];TransposedConvBinWinoRxS<2-3>:105;TransposedConvBinWinoRxS<3-2>:25
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:221
2x128x28x28x1x3x3x1x128x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:256
2x128x28x28x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:254
2x128x28x28x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:248
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:244
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:110;TransposedConvBinWinoRxS<3-2>:126
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:254
2x128x28x28x1x3x3x1x128x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];TransposedConvBinWinoRxS<2-3>:102;TransposedConvBinWinoRxS<3-2>:250
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:239
2x128x28x28x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:229
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:225
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:205
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:227
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];TransposedConvBinWinoRxS<2-3>:73;TransposedConvBinWinoRxS<3-2>:34
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:201
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;TransposedConvBinWinoRxS<3-2>:218
2x128x28x28x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:227
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:110
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:104
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:114
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:90;TransposedConvBinWinoRxS<3-2>:16
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];TransposedConvBinWinoRxS<3-2>:109
2x128x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:41
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x160x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x160x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x160x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x128x28x28x1x3x3x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x28x28x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x28x28x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x28x28x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x28x28x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x5x1x512x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x28x28x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x3x7x1x512x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x4x4x1x128x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x5x1x1x512x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:65
2x128x28x28x1x5x5x1x128x1x2x2x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x28x28x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147
2x128x28x28x1x7x7x1x128x1x3x3x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x7x7x1x128x4x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x28x28x1x9x9x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:146
2x128x296x296x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x29x29x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x29x29x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x29x29x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x29x29x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x29x29x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x29x29x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x29x29x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x29x29x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x29x29x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x29x29x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x29x29x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x29x29x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x29x29x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x29x29x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x29x29x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x29x29x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x29x29x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x29x29x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x29x29x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x29x29x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x29x29x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x29x29x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x29x29x1x4x4x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:71
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x29x29x1x6x6x1x128x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x2x2x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x2x2x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x2x2x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x30x30x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x30x30x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x30x30x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x30x30x1x3x3x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x30x30x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x32x32x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x32x32x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x128x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x32x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x32x32x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x32x32x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x32x32x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x32x32x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x32x32x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x32x32x1x3x3x1x128x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x32x32x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x32x32x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x32x32x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x32x32x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x32x32x1x5x5x1x128x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x32x32x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x32x32x1x7x7x1x128x4x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x32x32x1x7x7x1x256x1x3x3x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x34x34x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x34x34x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x34x34x1x7x7x1x128x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x37x173x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x37x173x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x37x173x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x37x173x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x37x173x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x37x173x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x37x173x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x37x173x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x37x173x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x37x173x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x173x1x5x5x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x173x1x5x5x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x173x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x173x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x38x173x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x173x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x38x173x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x173x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x38x173x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x38x173x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x38x173x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x38x173x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x173x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x173x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x38x174x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x174x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x38x174x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x38x174x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x174x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x128x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:94
2x128x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:239
2x128x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:182
2x128x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x128x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x128x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:252
2x128x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x1x1x1x64x112x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:253
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:245
2x128x38x38x1x1x1x1x64x114x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:255
2x128x38x38x1x1x1x1x64x120x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:251
2x128x38x38x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x38x38x1x1x1x1x64x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x1x1x1x64x24x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:255
2x128x38x38x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];TransposedConvBinWinoRxS<3-2>:47
2x128x38x38x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;TransposedConvBinWinoRxS<3-2>:237
2x128x38x38x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];TransposedConvBinWinoRxS<3-2>:67
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];TransposedConvBinWinoRxS<3-2>:65
2x128x38x38x1x1x1x1x64x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:100
2x128x38x38x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;TransposedConvBinWinoRxS<3-2>:247
2x128x38x38x1x1x1x1x64x56x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:241
2x128x38x38x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:249
2x128x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:69;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:243
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:100;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:246
2x128x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:66
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:234
2x128x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:80;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:253
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:246
2x128x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:75;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];TransposedConvBinWinoRxS<2-3>:75;TransposedConvBinWinoRxS<3-2>:31
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];TransposedConvBinWinoRxS<3-2>:255
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:27
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:246
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:248
2x128x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:117
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:59
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];TransposedConvBinWinoRxS<3-2>:54
2x128x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:77;TransposedConvBinWinoRxS<3-2>:18
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:233
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:227
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];TransposedConvBinWinoRxS<2-3>:85;TransposedConvBinWinoRxS<3-2>:69
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:68
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:67;TransposedConvBinWinoRxS<3-2>:18
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];TransposedConvBinWinoRxS<3-2>:82
2x128x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:88
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:106
2x128x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:98;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];TransposedConvBinWinoRxS<2-3>:82;TransposedConvBinWinoRxS<3-2>:20
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:242
2x128x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:67;TransposedConvBinWinoRxS<3-2>:16
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:242
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:227
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];TransposedConvBinWinoRxS<2-3>:73;TransposedConvBinWinoRxS<3-2>:19
2x128x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:245
2x128x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x128x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x128x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:92
2x128x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:245
2x128x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:177
2x128x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x128x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x38x38x1x3x3x1x64x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:250
2x128x38x38x1x3x3x1x64x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:244
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:249
2x128x38x38x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:256
2x128x38x38x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:246
2x128x38x38x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:255
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:254
2x128x38x38x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:57
2x128x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:236
2x128x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:69
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:69
2x128x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;TransposedConvBinWinoRxS<3-2>:88
2x128x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:249
2x128x38x38x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:243
2x128x38x38x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:232
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x128x39x174x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x39x174x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x39x174x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x39x174x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x39x174x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x174x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x39x175x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x39x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x175x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x175x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x39x175x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x39x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x175x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x175x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x39x175x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x39x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x175x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x175x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x39x39x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x39x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x39x39x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x39x39x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x39x39x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x39x39x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];TransposedConvBinWinoRxS<3-2>:36
2x128x3x3x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:63
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];TransposedConvBinWinoRxS<3-2>:38
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:34;TransposedConvBinWinoRxS<3-2>:32
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];TransposedConvBinWinoRxS<3-2>:45
2x128x3x3x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];TransposedConvBinWinoRxS<3-2>:32
2x128x3x3x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];TransposedConvBinWinoRxS<2-3>:34;TransposedConvBinWinoRxS<3-2>:49
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];TransposedConvBinWinoRxS<3-2>:41
2x128x3x3x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:39
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];TransposedConvBinWinoRxS<3-2>:17
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];TransposedConvBinWinoRxS<2-3>:54;TransposedConvBinWinoRxS<3-2>:33
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];TransposedConvBinWinoRxS<3-2>:10
2x128x3x3x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:40
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:65
2x128x3x3x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:37;TransposedConvBinWinoRxS<3-2>:40
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,185[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];TransposedConvBinWinoRxS<3-2>:12
2x128x3x3x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];TransposedConvBinWinoRxS<3-2>:8
2x128x3x3x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:34
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];TransposedConvBinWinoRxS<3-2>:15
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:41
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];TransposedConvBinWinoRxS<3-2>:10
2x128x3x3x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[6];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:36
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];TransposedConvBinWinoRxS<3-2>:18
2x128x3x3x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];TransposedConvBinWinoRxS<2-3>:46;TransposedConvBinWinoRxS<3-2>:38
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:141
2x128x3x3x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:37;TransposedConvBinWinoRxS<3-2>:34
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];TransposedConvBinWinoRxS<3-2>:16
2x128x3x3x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];TransposedConvBinWinoRxS<2-3>:50;TransposedConvBinWinoRxS<3-2>:34
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x3x3x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x3x3x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];TransposedConvBinWinoRxS<3-2>:16
2x128x3x3x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];TransposedConvBinWinoRxS<2-3>:55;TransposedConvBinWinoRxS<3-2>:32
2x128x3x3x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x3x3x1x3x3x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:12
2x128x3x3x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x400x544x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x400x544x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x4095x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x4095x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x4096x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x4096x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x4097x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x4097x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x40x175x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x40x175x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x40x175x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x40x175x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x40x175x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x40x175x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x40x175x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x40x175x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x1024x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x40x175x1x5x5x1x256x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x175x1x5x5x1x256x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x512x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x40x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x175x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x256x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x40x175x1x5x5x1x256x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x40x175x1x5x5x1x256x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x40x175x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x40x175x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x40x175x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x40x175x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x40x175x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x40x175x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x40x175x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x128x40x175x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x40x175x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x40x175x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x40x175x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x40x175x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x40x175x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x40x175x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x40x40x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x40x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x40x40x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x40x40x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x417x417x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x417x417x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x417x417x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x417x417x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3]
2x128x417x417x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x417x417x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x128x417x417x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x417x417x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5]
2x128x418x418x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x418x418x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7]
2x128x418x418x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x418x418x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x128x418x418x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x418x418x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x128x418x418x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x418x418x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5]
2x128x41x177x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x41x177x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x41x177x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x41x177x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x41x177x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x41x41x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x41x41x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x41x41x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x41x41x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x420x420x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x420x420x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x420x420x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x420x420x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x421x421x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x421x421x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x421x421x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x421x421x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x448x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x448x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x48x32x1x1x1x1x480x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x48x32x1x1x1x1x480x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x48x32x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x48x32x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x48x32x1x1x1x1x480x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x48x32x1x1x1x1x480x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x48x32x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x48x32x1x1x1x1x480x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x48x32x1x1x1x1x480x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x48x32x1x1x1x1x480x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x128x48x32x1x1x1x1x480x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x48x32x1x1x1x1x480x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x48x32x1x1x1x1x480x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x48x32x1x1x1x1x480x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x48x32x1x1x1x1x480x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x48x32x1x1x1x1x480x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x48x32x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x1x1x1x480x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x48x32x1x1x1x1x480x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x48x32x1x2x2x1x128x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 128, 64, OddC, 16, 16, 1, 4, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x48x32x1x2x2x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x48x32x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x48x32x1x2x2x1x128x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x48x32x1x2x2x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x48x32x1x2x2x1x128x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x48x48x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x48x48x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x48x48x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x4x16384x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x4x16x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x4x196x1x1x1x1x257x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x4x4096x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+1
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[1];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[4];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x4x4x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+1
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x4x4x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,45[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x4x4x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x4x4x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x4x4x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x4x4x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x4x4x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x4x4x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x4x4x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x512x512x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x512x512x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x512x512x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x128x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x512x512x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x512x512x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x128x512x512x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+128
2x128x512x512x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x512x512x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+128
2x128x512x512x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+128
2x128x512x512x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x512x512x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x512x512x1x1x1x1x259x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x512x512x1x1x1x1x260x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x512x512x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x512x512x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x512x512x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:236
2x128x512x512x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x512x512x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x512x512x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x144x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x128x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x128x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x512x512x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x512x512x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x128x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x512x512x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x513x513x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x513x513x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x52x52x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x52x52x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x544x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x544x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x54x54x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x54x54x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x54x54x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x54x54x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x54x54x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x54x54x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x54x54x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x54x54x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x54x54x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x54x54x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x54x54x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x54x54x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x54x54x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x54x54x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x54x54x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x54x54x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x55x55x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x55x55x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x55x55x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x55x55x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x55x55x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x55x55x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,83[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[4];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:36;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:34;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:235
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:82
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:228
2x128x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:34
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:251
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];TransposedConvBinWinoRxS<2-3>:58;TransposedConvBinWinoRxS<3-2>:33
2x128x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:253
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:237
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:39
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:36
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:45
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:245
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:246
2x128x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:35;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:255
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;TransposedConvBinWinoRxS<3-2>:255
2x128x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:38
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:35
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:249
2x128x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];TransposedConvBinWinoRxS<2-3>:40;TransposedConvBinWinoRxS<3-2>:34
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,83[2];TransposedConvBinWinoRxS<2-3>:113;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:233
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:34;TransposedConvBinWinoRxS<3-2>:33
2x128x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:254
2x128x56x56x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:51;TransposedConvBinWinoRxS<3-2>:34
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[9];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[8];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x56x56x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x128x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x128x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x128x56x56x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x128x4x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5]
2x128x56x56x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x128x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x128x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x144x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,197[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,134[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x256x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,8[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x128x56x56x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x56x56x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+128
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x128x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x56x56x1x4x4x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x56x56x1x4x4x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x56x56x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x56x56x1x5x5x1x256x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13
2x128x56x56x1x7x7x1x128x4x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:254
2x128x57x57x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x128x57x57x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:235
2x128x57x57x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:234
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x128x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:201
2x128x57x57x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:215
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x128x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x128x57x57x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:237
2x128x57x57x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:229
2x128x57x57x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x128x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+16
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x128x57x57x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:247
2x128x57x57x1x3x3x1x128x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x128x57x57x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:202
2x128x57x57x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:203
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x128x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x57x57x1x3x3x1x128x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x128x57x57x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x128x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x57x57x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:246
2x128x57x57x1x3x3x1x128x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x128x57x57x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x57x57x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:207
2x128x57x57x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:113
2x128x57x57x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:102
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x57x57x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x58x58x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x58x58x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x58x58x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x58x58x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x58x58x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x58x58x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x58x58x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x58x58x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x58x58x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x58x58x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x58x58x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x58x58x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x58x58x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x58x58x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x58x58x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x58x58x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x59x59x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x59x59x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x59x59x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x59x59x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x59x59x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x59x59x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x59x59x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x59x59x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x59x59x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x59x59x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x5x5x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;TransposedConvBinWinoRxS<3-2>:114
2x128x5x5x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:36;TransposedConvBinWinoRxS<3-2>:35
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;TransposedConvBinWinoRxS<3-2>:121
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:49;TransposedConvBinWinoRxS<3-2>:33
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;TransposedConvBinWinoRxS<3-2>:125
2x128x5x5x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:37;TransposedConvBinWinoRxS<3-2>:34
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:121
2x128x5x5x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:52;TransposedConvBinWinoRxS<3-2>:36
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:130
2x128x5x5x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:65
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x5x5x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x5x5x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];TransposedConvBinWinoRxS<3-2>:28
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];TransposedConvBinWinoRxS<2-3>:36;TransposedConvBinWinoRxS<3-2>:35
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];TransposedConvBinWinoRxS<3-2>:29
2x128x5x5x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:256
2x128x5x5x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:41;TransposedConvBinWinoRxS<3-2>:34
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[9];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];TransposedConvBinWinoRxS<3-2>:15
2x128x5x5x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];TransposedConvBinWinoRxS<2-3>:34;TransposedConvBinWinoRxS<3-2>:34
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];TransposedConvBinWinoRxS<3-2>:32
2x128x5x5x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];TransposedConvBinWinoRxS<2-3>:35;TransposedConvBinWinoRxS<3-2>:37
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];TransposedConvBinWinoRxS<3-2>:20
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:32
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,57[3];TransposedConvBinWinoRxS<3-2>:27
2x128x5x5x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[9];TransposedConvBinWinoRxS<2-3>:36;TransposedConvBinWinoRxS<3-2>:40
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[9];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];TransposedConvBinWinoRxS<3-2>:11
2x128x5x5x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[7];TransposedConvBinWinoRxS<2-3>:51;TransposedConvBinWinoRxS<3-2>:40
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x128x5x5x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:55;TransposedConvBinWinoRxS<3-2>:32
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];TransposedConvBinWinoRxS<3-2>:60
2x128x5x5x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:50;TransposedConvBinWinoRxS<3-2>:33
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];TransposedConvBinWinoRxS<3-2>:66
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];TransposedConvBinWinoRxS<2-3>:35;TransposedConvBinWinoRxS<3-2>:35
2x128x5x5x1x3x3x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:59
2x128x5x5x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2]
2x128x5x5x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:35
2x128x5x5x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:68
2x128x5x5x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:77
2x128x5x5x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:34
2x128x5x5x1x3x3x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:44
2x128x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:35
2x128x5x5x1x3x3x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:147
2x128x5x5x1x3x3x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x5x5x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:31
2x128x5x5x1x3x3x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:25
2x128x5x5x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x60x60x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x60x60x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x60x60x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x62x62x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x62x62x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x62x62x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x62x62x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x640x640x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x640x640x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x64x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x128x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x128x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x64x64x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x64x64x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x3x3x1x256x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x3x3x1x512x1x2x2x0x2x2x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x64x64x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x64x64x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x64x64x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x64x64x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x64x64x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x64x64x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x64x64x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x5x5x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x5x5x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x64x64x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x7x7x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x64x64x1x7x7x1x128x1x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x64x64x1x7x7x1x128x8x3x3x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x64x64x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x64x64x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x65x65x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x65x65x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x65x65x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x65x65x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x128x65x65x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x65x65x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x128x66x66x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x66x66x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x66x66x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x6x60x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x6x60x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x6x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x6x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x6x60x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x6x60x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x6x60x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x6x60x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x6x60x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x6x60x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x6x60x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x6x60x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x6x60x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x6x60x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x6x60x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x128x6x60x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x6x60x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x6x60x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x6x60x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x6x60x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x6x60x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x6x60x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x6x60x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x6x60x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x72x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x72x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x72x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x72x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x72x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x72x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x72x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x74x74x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x74x74x1x4x4x1x128x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x75x75x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x128x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x128x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x128x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x768x768x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x128x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x128x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119
2x128x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x76x346x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x76x346x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,79[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x76x346x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x76x346x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x76x346x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x76x346x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x76x346x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x76x346x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x76x346x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x76x346x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x78x348x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x78x348x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x78x348x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x78x348x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x128x78x348x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x78x348x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x78x348x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x78x348x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[9];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[4];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1088x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1088x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1088x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1120x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1120x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[7];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1184x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1184x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1216x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1216x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1216x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[7];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1312x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+2
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1312x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1376x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1376x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1376x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,81[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1408x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1408x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1472x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1472x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1472x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1472x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1504x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1504x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1568x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1568x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1568x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1600x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+2
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1600x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1664x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[9];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1664x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1664x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1664x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1696x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1696x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[4];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1760x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,113[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1760x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1760x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1760x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1856x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1856x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1856x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1888x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[7];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1888x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x1888x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,9[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,45[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,3,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,81[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x544x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x544x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,45[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x608x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x608x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x608x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x608x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,29[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x640x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[10];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x704x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x704x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x704x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,45[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[10];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x736x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,81[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x736x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x736x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,57[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x800x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,3,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,29[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 32, 64, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[8];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x928x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x928x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x928x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x928x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x928x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 32, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x992x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x1x1x1x992x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x1x1x1x992x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x992x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x128x7x7x1x1x1x1x992x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x128x7x7x1x1x1x1x992x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x7x7x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x128x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[7];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x7x7x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+64
2x128x7x7x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x128x7x7x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x128x7x7x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,2,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x128x7x7x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+32
2x128x7x7x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x128x7x7x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x7x7x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,247[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x128x7x7x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x48x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x5x5x1x48x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x128x7x7x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x128x7x7x1x5x5x1x832x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x5x5x1x832x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x128x7x7x1x5x5x1x832x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x128x7x7x1x5x5x1x832x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x5x5x1x832x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x7x7x1x5x5x1x832x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x128x7x7x1x5x5x1x832x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x5x5x1x832x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x128x7x7x1x5x5x1x832x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x5x5x1x832x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x7x7x1x5x5x1x832x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x7x7x1x5x5x1x832x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x128x7x7x1x5x5x1x832x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x7x7x1x7x7x1x128x1x9x9x0x1x1x0x3x3x0x0x128xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x80x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x80x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x108x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x108x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x108x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x108x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x108x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x108x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x80x108x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x80x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x80x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x80x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x80x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x80x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x80x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x80x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x80x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x80x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x80x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x80x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x80x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x80x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x80x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x80x350x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x80x350x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x80x350x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x128x80x350x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x128x80x350x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x128x80x350x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x80x350x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x80x350x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x80x350x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x128x80x350x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x128x80x350x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x128x80x350x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x128x80x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x80x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x80x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x80x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x80x1x3x1x1x128x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x80x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x80x80x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x80x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x80x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x80x80x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x80x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x80x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x80x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x80x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x80x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x80x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x104x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x84x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x104x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x104x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x104x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x84x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x104x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x104x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x84x104x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x84x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x112x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x112x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x112x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x84x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x84x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x84x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x128x84x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x84x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x84x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x84x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x128x84x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x84x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x84x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x84x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x84x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x84x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x84x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x84x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x84x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x84x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x84x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x84x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x84x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x84x84x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x84x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x84x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x84x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x88x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x88x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x88x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x100x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x88x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x88x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x88x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x88x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x88x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x88x120x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x88x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x88x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x132x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x132x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x132x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x132x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x88x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x88x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x132x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x88x132x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x88x132x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x88x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x88x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x88x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x88x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x88x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x88x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x88x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x88x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x88x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x88x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x88x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x88x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x88x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x88x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x88x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x88x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x88x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x88x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x88x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x88x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x88x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x88x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x88x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x88x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x8x8x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x8x8x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x128x8x8x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x128x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x128x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x128x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x128x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x128x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x128x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x92x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x92x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x92x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x116x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x92x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x92x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x92x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x92x124x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x92x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x92x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x92x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x92x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x92x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x140x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x140x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x140x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x140x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x92x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x140x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x92x140x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x140x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x92x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x92x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x92x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x92x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x92x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x92x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x128x92x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x92x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x92x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x92x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x92x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x128x92x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x92x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x92x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x92x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x92x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x92x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x92x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x92x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x92x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x92x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x128x92x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x92x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x92x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x92x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x92x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x92x92x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x96x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x104x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x96x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x108x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x96x108x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x108x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x96x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x96x116x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x120x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x124x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x128x96x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x96x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x96x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x132x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x128x96x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x96x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x140x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x144x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x96x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x96x144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x144x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x128x96x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x96x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x148x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x128x96x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x148x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x96x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x156x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x96x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x156x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x96x156x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x156x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x156x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x156x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x156x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x96x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x156x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x160x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x96x160x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x96x160x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x160x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x96x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x160x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x160x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x160x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x160x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x128x96x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x164x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x128x96x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x96x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x128x96x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x168x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x168x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x128x96x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x128x96x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x128x96x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x128x96x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x128x96x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x128x96x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x96x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x128x96x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x96x88x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x128x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x128x96x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x128x96x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x128x96x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x128x96x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x96x96x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x96x96x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x96x96x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x97x97x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x128x9x9x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x128x9x9x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x9x9x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x128x9x9x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x9x9x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x128x9x9x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x128x9x9x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x128x9x9x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x128x9x9x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x1296x128x128x1x3x3x1x1296x1x1x1x0x2x2x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1296x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1296x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1296x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1296x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1296x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1296x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1296x14x14x1x3x3x1x1296x1x1x1x0x1x1x0x1x1x0x0x1296xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1296x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x32x32x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x64x64x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x64x64x1x3x3x1x1296x1x1x1x0x1x1x0x1x1x0x0x1296xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1296x64x64x1x3x3x1x1296x4x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1296x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1296x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1296x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1296x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1296x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1296x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1296x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1296x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1296x7x7x1x3x3x1x1296x4x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x12x100x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x100x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x100x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x100x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x100x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x100x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x100x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x100x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x100x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x100x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x100x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x1024x1024x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x12x1024x1024x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x12x1024x1024x1x3x3x1x12x1x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x12x1024x1024x1x3x3x1x12x4x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x12x104x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x104x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x104x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x104x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x104x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x104x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x104x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x104x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x108x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x108x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x108x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x108x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x108x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x108x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x10x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x10x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x12x10x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x10x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x10x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x10x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x12x10x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x10x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x112x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x112x112x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x112x112x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x112x112x1x3x3x1x12x1x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x12x112x112x1x3x3x1x12x4x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x12x112x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x112x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x112x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x112x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x112x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x113x113x1x2x2x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x113x113x1x2x2x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x116x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x116x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x116x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x116x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x116x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x116x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x116x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x116x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x116x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x116x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x116x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x116x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x11x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x12x11x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x12x11x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x11x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x11x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[9];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x11x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x11x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x11x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x11x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x11x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x11x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x120x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x120x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x120x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x120x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x120x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x120x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x120x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x124x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x124x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x124x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x124x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x124x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x124x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x124x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x124x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x124x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x124x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x124x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x124x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x128x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x128x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x128x128x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:252
2x12x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1]
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x128x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x128x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x128x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x128x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x12x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x12x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x12x12x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x12x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x12x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x12x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[10];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x12x12x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x12x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x12x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x12x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x12x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x12x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x12x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x132x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x132x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x132x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x132x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x132x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x132x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x132x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x136x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x136x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x136x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x136x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x136x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x136x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x136x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x136x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x136x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x136x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x136x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x136x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x13x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x13x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[9];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x13x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x13x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x13x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x13x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x140x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x140x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x140x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x140x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x140x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x140x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x140x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x140x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x140x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x140x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x144x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x144x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x144x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x12x144x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x144x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x144x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x144x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x144x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x144x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x144x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x148x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x148x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x148x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x148x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x148x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x148x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x148x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x148x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x148x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x148x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x14x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x12x14x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x14x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x14x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x12x152x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x152x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x152x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x152x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x152x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x152x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x152x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x152x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x152x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x152x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x156x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x156x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x156x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x156x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x156x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x156x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x15x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x15x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x15x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x12x15x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x15x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x15x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x15x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x15x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x160x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x160x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x160x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x160x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x160x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x160x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x164x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x164x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x164x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x164x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x168x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x168x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x168x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x16x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x16x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x16x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x16x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x16x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x16x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x16x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x16x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x16x16x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x16x16x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x16x16x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x16x16x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x16x16x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x12x16x16x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x16x16x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x16x16x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x16x16x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x16x16x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x16x16x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x16x16x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x16x16x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x16x16x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x16x16x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x16x16x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x17x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x17x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x17x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x17x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x18x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x18x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x19x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x19x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x19x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x19x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x19x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x19x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x1x1x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x12x1x1x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x12x1x1x1x1x1x1x215x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x1x1x1x1x1x1x36x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x1x1x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x1x1x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x12x1x1x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+1
2x12x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x12x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+1
2x12x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x20x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x12x20x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x20x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x20x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x20x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x20x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x20x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x20x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x20x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x20x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x12x20x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x20x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x20x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x21x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x21x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x21x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x12x21x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x21x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x21x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x21x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x21x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x21x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x21x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x21x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x21x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x21x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x21x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x21x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x21x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x21x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x21x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x21x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x22x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x22x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x22x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x22x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x22x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x22x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x22x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x22x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x23x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x23x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x23x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x23x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x23x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x23x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x23x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x23x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x23x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x23x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x23x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x23x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x12x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x24x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x24x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x24x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x24x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x24x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x256x256x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x256x256x1x1x1x1x49x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x256x256x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+-1
2x12x256x256x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x256x256x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x256x256x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:255
2x12x256x256x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+128
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x256x256x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8]
2x12x256x256x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x256x256x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x256x256x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x25x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x25x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x25x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x25x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x25x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x25x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x25x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x25x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x25x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x25x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x25x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x25x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x25x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x25x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x25x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x25x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x26x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x26x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x26x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x26x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x26x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x26x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x27x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x27x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x27x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x27x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x27x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x27x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x27x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x27x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x28x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x28x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x28x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x28x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x28x28x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x12x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x29x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x29x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x29x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x29x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x29x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x29x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x29x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x29x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x30x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x30x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x30x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x30x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x30x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x30x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x30x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x30x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x30x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x30x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x31x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x31x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x31x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x31x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x31x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x31x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x31x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x31x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x31x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x31x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x32x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x32x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x32x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,11[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x32x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x32x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x32x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x32x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x32x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x32x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x12x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x12x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x33x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x12x33x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x33x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x33x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x33x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x12x33x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x33x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x34x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x34x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x12x34x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x34x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x34x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x34x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x34x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x34x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x34x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x34x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x34x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x34x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x35x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x35x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x35x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x35x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x35x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x35x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x36x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x36x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x36x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x36x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x36x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x36x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x37x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x37x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x37x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x37x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x37x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x37x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x38x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x38x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x38x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x38x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x38x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x38x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x38x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x38x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x39x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x12x39x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x40x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x40x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x40x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x40x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x40x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x40x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x40x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x40x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x40x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x40x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x12x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x40x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x40x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x40x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x40x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x41x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x41x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x41x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x41x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x42x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x42x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x12x42x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x42x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x42x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x42x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x42x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x42x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x12x42x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x42x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x42x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x42x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x12x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x42x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x42x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x42x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x42x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x42x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x42x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x44x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x44x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x44x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x46x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x46x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x46x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x46x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x12x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x50x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x50x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x50x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x512x512x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x512x512x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x12x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x12x512x512x1x1x1x1x49x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x512x512x1x1x1x1x62x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x512x512x1x1x1x1x70x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x512x512x1x3x3x1x12x1x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x12x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x54x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x54x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x54x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x54x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x54x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x54x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x56x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x56x56x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x56x56x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x56x56x1x1x1x1x36x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x56x56x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x12x56x56x1x1x1x1x49x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x56x56x1x1x1x1x49x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x56x56x1x1x1x1x62x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x12x56x56x1x3x3x1x12x1x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x12x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x60x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x60x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x60x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x60x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x12x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x62x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x62x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x62x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x62x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x62x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x64x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x64x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x64x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x64x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x64x64x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x64x64x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x64x64x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x64x64x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x64x64x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x64x64x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x12x64x64x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:255
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x64x64x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x12x64x64x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x64x64x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x64x64x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x68x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x68x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x68x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x68x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x70x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x70x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x70x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x70x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x70x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x70x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x72x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x72x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x72x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x72x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x74x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x74x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x74x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x74x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x76x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x76x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x76x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x12x76x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x78x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x78x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x78x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x78x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x80x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x80x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x80x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x80x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x80x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x80x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x80x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x80x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x80x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x80x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x80x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x80x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x80x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x82x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x82x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x82x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x82x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x12x84x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x84x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x84x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x84x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x84x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x84x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x84x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x12x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x84x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x84x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x88x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x88x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x88x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x88x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x88x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x88x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x12x88x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x88x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x88x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x88x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x88x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x88x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x88x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x88x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x92x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x12x92x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x12x92x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x92x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x92x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x92x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x92x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x12x92x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x12x96x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x12x96x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x12x96x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x12x96x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x1302x128x128x1x3x3x1x1302x1x1x1x0x1x1x0x1x1x0x0x1302xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1302x14x14x1x1x1x1x250x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1302x64x64x1x3x3x1x1302x1x1x1x0x1x1x0x1x1x0x0x1302xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x130x128x128x1x3x3x1x130x1x1x1x0x1x1x0x1x1x0x0x130xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,18[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1312x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1312x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1312x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1312x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1312x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1312x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1312x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1312x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1312x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1312x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1320x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1320x32x32x1x5x5x1x1320x1x2x2x0x1x1x0x1x1x0x0x1320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1320x64x64x1x5x5x1x1320x4x2x2x0x1x1x0x1x1x0x0x1320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1320x7x7x1x5x5x1x1320x4x2x2x0x1x1x0x1x1x0x0x1320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1328x128x128x1x1x1x1x332x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1328x128x128x1x1x1x1x664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1328x128x128x1x1x1x1x664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1328x14x14x1x1x1x1x332x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1328x14x14x1x1x1x1x332x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1328x14x14x1x1x1x1x664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x132x128x128x1x3x3x1x132x4x1x1x0x1x1x0x1x1x0x0x132xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x132x1x1x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x132x1x1x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x132x1x1x1x1x1x1x532x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x132x256x256x1x3x3x1x132x4x1x1x0x2x2x0x1x1x0x0x132xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x132x28x28x1x3x3x1x132x1x1x1x0x1x1x0x1x1x0x0x132xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x132x64x64x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1336x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1336x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1336x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1336x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x11x11x1x1x1x1x2688x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1344x11x11x1x1x1x1x2688x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x1344x11x11x1x1x1x1x4032x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x1344x11x11x1x1x1x1x4032x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x1344x11x11x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x128x128x1x1x1x1x2520x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x128x128x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x128x128x1x3x3x1x1344x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1344x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1344x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1344x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x2520x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x1x1x1x2520x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x14x14x1x3x3x1x1344x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x14x14x1x3x3x1x1344x4x1x1x0x1x1x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x14x14x1x5x5x1x1344x1x2x2x0x1x1x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x15x15x1x3x3x1x1344x1x0x0x0x2x2x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x1x1x1x1x1x1x1984x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x21x21x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x28x28x1x3x3x1x1344x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x32x32x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x32x32x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x37x37x1x5x5x1x1344x1x2x2x0x1x1x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x64x64x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x64x64x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x64x64x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x64x64x1x3x3x1x1344x4x1x1x0x1x1x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x64x64x1x5x5x1x1344x1x2x2x0x1x1x0x1x1x0x0x1344xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1344x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1344x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1344x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1344x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1344x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1344x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1344x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1356x1x1x1x1x1x1x113x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1356x32x32x1x1x1x1x243x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1356x64x64x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1356x64x64x1x1x1x1x243x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1356x64x64x1x3x3x1x1356x4x1x1x0x1x1x0x1x1x0x0x1356xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1360x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1360x64x64x1x1x1x1x1360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1360x64x64x1x1x1x1x1360x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1360x64x64x1x3x3x1x1360x1x1x1x0x2x2x0x1x1x0x0x34xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1360x64x64x1x3x3x1x1360x4x1x1x0x1x1x0x1x1x0x0x34xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x136x1024x1024x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x136x1024x1024x1x3x3x1x136x1x1x1x0x1x1x0x1x1x0x0x136xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x136x1024x1024x1x3x3x1x136x4x1x1x0x1x1x0x1x1x0x0x136xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x136x512x512x1x3x3x1x136x1x1x1x0x1x1x0x1x1x0x0x136xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1376x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1376x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1376x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1376x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1376x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1376x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x64x64x1x1x1x1x8256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1376x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1376x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1376x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1376x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1376x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1376x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x137x128x128x1x1x1x1x74x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x137x128x128x1x3x3x1x137x1x1x1x0x1x1x0x1x1x0x0x137xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x137x14x14x1x3x3x1x137x4x1x1x0x1x1x0x1x1x0x0x137xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1384x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x10x10x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x10x10x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x10x10x1x5x5x1x1392x1x2x2x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1392x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x128x128x1x1x1x1x3712x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x128x128x1x1x1x1x3712x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1392x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1392x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1392x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x1x1x1x3712x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x14x14x1x3x3x1x1392x1x1x1x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1392x14x14x1x3x3x1x1392x4x1x1x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1392x1x1x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x1x1x1x1x1x1x174x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x1x1x1x1x1x1x174x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x1x1x1x1x1x1x348x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x256x256x1x3x3x1x1392x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x32x32x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x32x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x32x32x1x3x3x1x1392x1x1x1x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1392x64x64x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1392x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1392x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1392x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1392x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1392x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1392x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1392x7x7x1x3x3x1x1392x1x1x1x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1392x7x7x1x3x3x1x1392x4x1x1x0x1x1x0x1x1x0x0x1392xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x13x1024x1024x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x1024x1024x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x112x112x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x112x112x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x13x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x13x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:251
2x13x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x13x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x13x19x19x1x3x3x1x64x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x13x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x13x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x13x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x13x512x512x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1404x128x128x1x1x1x1x257x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1404x14x14x1x1x1x1x257x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1408x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1408x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x128x128x1x2x2x1x2816x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x128x128x1x3x3x1x1408x4x1x1x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x128x128x1x5x5x1x1408x1x2x2x0x2x2x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x128x128x1x5x5x1x1408x4x2x2x0x2x2x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x128x128x1x7x7x1x1408x1x3x3x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x128x128x1x7x7x1x1408x4x3x3x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1408x128x128x1x9x9x1x1408x4x4x4x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1408x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1408x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1408x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x2820x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x14x14x1x2x2x1x2816x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x3x3x1x2816x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x14x14x1x5x5x1x1408x4x2x2x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x14x14x1x5x5x1x1408x4x2x2x0x2x2x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x14x14x1x9x9x1x1408x4x4x4x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x512x512x1x1x1x1x352x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x64x64x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x64x64x1x5x5x1x1408x1x2x2x0x2x2x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1408x64x64x1x9x9x1x1408x1x4x4x0x1x1x0x1x1x0x0x1408xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1408x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1408x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1408x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1408x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1408x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1408x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1408x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x140x128x128x1x3x3x1x140x1x1x1x0x1x1x0x1x1x0x0x140xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x140x128x128x1x3x3x1x140x4x1x1x0x1x1x0x1x1x0x0x140xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x140x14x14x1x3x3x1x140x4x1x1x0x1x1x0x1x1x0x0x140xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x140x1x1x1x1x1x1x36x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x141x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x142x128x128x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x142x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x142x14x14x1x1x1x1x852x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x142x256x256x1x1x1x1x122x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x142x28x28x1x1x1x1x102x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x142x28x28x1x1x1x1x122x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1432x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1440x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1440x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1440x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1440x1x1x1x1x1x1x1984x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x32x32x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1440x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x64x64x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1440x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1440x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1440x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1440x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1440x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1440x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1440x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1440x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1440x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1440x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x1025x1025x1x3x3x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x144x112x112x1x3x3x1x144x4x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x112x112x1x3x3x1x144x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x114x114x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x128x128x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x128x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x128x128x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x128x128x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x128x128x1x5x5x1x144x1x2x2x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x128x128x1x7x7x1x144x4x3x3x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[10];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x144x131x131x1x3x3x1x144x4x0x0x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x14x14x1x11x11x1x144x1x5x5x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x144x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x144x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x144x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x144x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x144x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x144x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x144x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x144x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x14x14x1x3x3x1x144x4x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x14x14x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x14x14x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x14x14x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x14x14x1x3x3x1x288x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x14x14x1x3x3x1x288x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x14x14x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x14x14x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x14x14x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x144x14x14x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x144x14x14x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x144x14x14x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x144x14x14x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x14x14x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x144x14x14x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x14x14x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x14x14x1x7x7x1x144x1x3x3x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x14x14x1x9x9x1x144x4x4x4x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x191x191x1x3x3x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x19x19x1x7x7x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x1x1x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x1x1x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x1x1x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x1x1x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x144x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+1
2x144x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x144x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x144x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+1
2x144x20x20x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x21x21x1x3x3x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x144x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x144x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x144x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x144x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x144x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x144x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x144x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x144x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x144x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x144x24x16x1x3x3x1x144x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x144x24x16x1x3x3x1x144x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x144x24x16x1x3x3x1x144x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x144x24x16x1x3x3x1x144x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x144x24x16x1x3x3x1x144x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x3x3x1x144x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x3x3x1x144x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x3x3x1x144x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,290[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x3x3x1x144x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x24x16x1x3x3x1x144x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x3x3x1x144x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x144x24x16x1x3x3x1x144x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x3x3x1x144x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x3x3x1x144x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x3x3x1x144x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x3x3x1x144x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x3x3x1x144x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x3x3x1x144x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x144x24x16x1x3x3x1x144x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x24x16x1x3x3x1x144x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x5x5x1x144x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x5x5x1x144x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x5x5x1x144x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x144x24x16x1x5x5x1x144x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x5x5x1x144x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x144x24x16x1x5x5x1x144x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x5x5x1x144x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x24x16x1x5x5x1x144x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x144x24x16x1x5x5x1x144x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x144x24x16x1x5x5x1x144x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x144x24x16x1x5x5x1x144x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x144x24x16x1x5x5x1x144x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x5x5x1x144x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x5x5x1x144x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x144x24x16x1x5x5x1x144x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x144x24x16x1x5x5x1x144x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x24x16x1x5x5x1x144x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x24x16x1x5x5x1x144x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x5x5x1x144x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x144x24x16x1x5x5x1x144x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x144x24x16x1x5x5x1x144x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x144x24x16x1x5x5x1x144x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x24x16x1x5x5x1x144x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x144x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x256x256x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x256x256x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x258x258x1x3x3x1x144x1x0x0x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x258x258x1x3x3x1x144x4x0x0x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x144x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x28x28x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x3x3x1x144x16x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x28x28x1x3x3x1x144x16x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x28x28x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x3x3x1x144x32x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x28x28x1x3x3x1x144x32x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x144x28x28x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x3x3x1x144x64x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x28x28x1x3x3x1x144x64x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x144x28x28x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x28x28x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x5x5x1x144x16x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x5x5x1x144x32x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x5x5x1x144x64x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x29x29x1x3x3x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x29x29x1x3x3x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x2x2x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x30x30x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x32x32x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x32x32x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x3x3x1x3x3x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x4x4096x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x4x49x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x512x512x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x512x512x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x512x512x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x512x512x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x512x512x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x512x512x1x5x5x1x144x4x2x2x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x513x513x1x3x3x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x144x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x144x56x56x1x1x1x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x1x1x1x41x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x144x56x56x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x56x56x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x56x56x1x3x3x1x144x16x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x56x56x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x56x56x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x56x56x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x56x56x1x3x3x1x144x32x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x144x56x56x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x144x56x56x1x3x3x1x144x64x1x1x0x2x2x0x1x1x0x0x144xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x59x59x1x5x5x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x60x60x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x63x63x1x5x5x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x63x63x1x5x5x1x144x4x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x144x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x144x64x128x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x64x128x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x436x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x64x64x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x64x64x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x64x64x1x1x1x1x872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x64x64x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x65x65x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x65x65x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x71x71x1x9x9x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x73x73x1x11x11x1x144x1x0x0x0x2x2x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x144x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x1x1x1x36x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x144x7x7x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x144x7x7x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x144x7x7x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x144x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x144x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x144x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x144x7x7x1x1x1x1x872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x144x7x7x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x7x7x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1456x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1458x1x1x1x1x1x1x121x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1458x1x1x1x1x1x1x121x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1458x32x32x1x3x3x1x1458x1x1x1x0x1x1x0x1x1x0x0x1458xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1458x7x7x1x3x3x1x1458x1x1x1x0x1x1x0x1x1x0x0x1458xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1472x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x128x128x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1472x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1472x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1472x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1472x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x64x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x64x64x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1472x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1472x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1472x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1472x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1472x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1472x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1472x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1480x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1480x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x128x128x1x1x1x1x248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x128x128x1x1x1x1x248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1488x131x131x1x5x5x1x1488x1x0x0x0x2x2x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1488x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1488x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1488x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1488x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x1x1x1x248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x14x14x1x5x5x1x1488x1x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x1x1x1x1x1x1x62x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x64x64x1x5x5x1x1488x1x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x67x67x1x5x5x1x1488x1x0x0x0x2x2x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1488x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1488x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1488x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1488x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1488x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1488x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x416x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1488x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x416x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1488x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1488x7x7x1x1x1x1x416x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x424x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x1x1x1x424x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1488x7x7x1x3x3x1x1488x16x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x32x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x3x3x1x1488x64x1x1x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x5x5x1x1488x16x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1488x7x7x1x5x5x1x1488x32x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1488x7x7x1x5x5x1x1488x64x2x2x0x1x1x0x1x1x0x0x1488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x148x14x14x1x3x3x1x148x4x1x1x0x1x1x0x1x1x0x0x148xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x149x128x128x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x149x128x128x1x1x1x1x894x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x149x256x256x1x1x1x1x894x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x149x256x256x1x1x1x1x894x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x14x1x1x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+4
2x14x1x1x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x14x1x1x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x14x1x1x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+4
2x14x1x1x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x14x1x1x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x14x256x256x1x3x3x1x14x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x14x512x512x1x3x3x1x14x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x1500x1x1x1x1x1x1x125x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1504x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1504x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1504x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1504x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1504x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1504x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1504x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1504x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1504x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1504x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1504x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1504x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178
2x1504x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1504x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1504x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1504x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1512x128x128x1x3x3x1x1512x4x1x1x0x2x2x0x1x1x0x0x63xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1512x1x1x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1512x64x64x1x3x3x1x1512x1x1x1x0x2x2x0x1x1x0x0x63xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1512x7x7x1x1x1x1x1512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1512x7x7x1x1x1x1x1512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x151x1x1x1x1x1x1x1812x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x151x32x32x1x1x1x1x906x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x151x7x7x1x1x1x1x906x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1528x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1528x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1528x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1528x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x152x128x128x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x152x128x128x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x152x128x128x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x152x128x128x1x3x3x1x152x1x1x1x0x1x1x0x1x1x0x0x19xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x128x128x1x3x3x1x152x4x1x1x0x1x1x0x1x1x0x0x19xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x128x128x1x3x3x1x304x1x1x1x0x2x2x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x14x14x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x152x14x14x1x1x1x1x368x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x14x14x1x1x1x1x368x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x152x14x14x1x2x2x1x152x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x1x1x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x152x256x256x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x256x256x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x152x256x256x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x152x256x256x1x7x7x1x152x1x3x3x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x256x256x1x7x7x1x304x4x3x3x0x2x2x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x28x28x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x28x28x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x28x28x1x2x2x1x152x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x152x28x28x1x3x3x1x152x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x152x28x28x1x3x3x1x304x4x1x1x0x2x2x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x28x28x1x7x7x1x152x4x3x3x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x56x56x1x2x2x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x152x56x56x1x3x3x1x152x4x1x1x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x152x7x7x1x3x3x1x152x1x1x1x0x1x1x0x1x1x0x0x152xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1536x128x128x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x128x128x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x128x128x1x3x3x1x1536x1x1x1x0x2x2x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1536x128x128x1x3x3x1x1536x4x1x1x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x128x128x1x3x3x1x1536x4x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x128x1x1x3x1x1x1536x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x128x1x1x3x1x1x1536x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1536x12x12x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x146x146x1x9x9x1x1536x1x4x4x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x147x147x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1536x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x14x14x1x3x3x1x1536x4x1x1x0x2x2x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x16x16x1x1x1x1x6144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x16x16x1x3x3x1x1536x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x16x16x1x3x3x1x1536x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x16x16x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1194x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1194x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1209x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1209x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1211x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1211x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x1234x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1234x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x123x1x1x1x1x768x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x123x1x1x1x1x768x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1246x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x1246x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x124x1x1x1x1x768x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x124x1x1x1x1x768x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x125x1x1x1x1x768x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x125x1x1x1x1x768x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x1x128x1x1x3x1x1536x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1536x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x149x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x149x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x150x1x1x1x1x768x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x150x1x1x1x1x768x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x152x1x1x1x1x768x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x152x1x1x1x1x768x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x152x1x1x1x1x768x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x152x1x1x1x1x768x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x153x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x153x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x154x1x1x1x1x768x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x154x1x1x1x1x768x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x155x1x1x1x1x768x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x155x1x1x1x1x768x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x156x1x1x1x1x768x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x156x1x1x1x1x768x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x182x1x1x1x1x768x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x182x1x1x1x1x768x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x183x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x183x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x184x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x184x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x184x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x184x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x185x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x185x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x186x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x186x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x187x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x187x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x187x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x187x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x188x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x188x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x188x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x188x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x189x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x189x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x190x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x190x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x191x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x191x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x191x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x191x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x192x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x192x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x193x1x1x1x1x768x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x193x1x1x1x1x768x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x1x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x1x1x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x1x1x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x226x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x226x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x227x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x227x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x228x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x228x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x229x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x229x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x230x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x230x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x231x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x231x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x232x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x232x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x233x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x233x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x234x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x234x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x234x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x234x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x235x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x235x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x236x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x236x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x236x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x236x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x237x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x237x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x238x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x238x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x239x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x239x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x240x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x240x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x241x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x241x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x242x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x242x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x243x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x243x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x244x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x244x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x245x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x245x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x246x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x246x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x247x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x247x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x248x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x248x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x249x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x249x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x250x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x250x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x251x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x251x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x252x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x252x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x253x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x253x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x253x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x253x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x254x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x254x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x255x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x255x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x256x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x256x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x257x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x257x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x258x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x258x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x258x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x258x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x259x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x259x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x260x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x260x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x261x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x261x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x262x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x262x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x263x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x263x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x264x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x264x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x265x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x265x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x266x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x266x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x266x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x266x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x268x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x268x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x269x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x269x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x269x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x269x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x26x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x1536x1x26x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x26x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1536x1x26x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x270x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x270x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x271x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x271x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x272x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x272x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x272x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x272x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x273x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x273x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x274x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x274x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x275x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x275x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x275x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x275x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x276x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x276x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x277x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x277x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x278x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x278x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x278x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x278x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x279x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x279x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x280x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x280x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x281x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x281x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x281x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x281x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x282x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x282x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x283x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x283x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x284x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x284x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x285x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x285x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x286x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x286x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x287x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x287x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x288x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x288x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x289x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x289x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x291x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x291x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x291x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x291x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x292x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x292x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x293x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x293x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x294x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x294x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x295x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x295x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x296x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x296x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x297x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x297x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x298x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x298x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x298x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x298x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x299x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x299x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x300x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x300x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x301x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x301x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x302x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x302x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x304x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x304x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x305x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x305x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x305x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x305x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x306x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x306x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x307x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x307x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x308x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x308x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x309x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x309x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x309x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x309x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x310x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x310x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x311x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x311x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x312x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x312x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x313x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x313x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x313x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x313x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x314x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x314x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x315x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x315x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x316x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x316x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x317x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x317x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x318x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x318x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x319x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x319x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x320x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x320x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x321x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x321x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x321x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x321x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x322x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x322x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x324x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x324x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x325x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x325x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x325x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x325x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x326x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x326x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x327x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x327x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x328x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x328x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x329x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x329x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x329x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x329x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x330x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x330x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x331x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x331x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x332x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x332x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x333x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x333x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x334x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x334x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x335x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x335x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x336x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x336x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x337x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x337x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x338x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x338x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x339x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x339x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x33x1x1x1x1x768x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x33x1x1x1x1x768x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x340x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x340x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x341x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x341x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x342x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x342x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x343x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x343x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x344x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x344x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x345x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x345x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x346x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x346x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x347x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x347x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x348x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x348x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x349x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x349x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x350x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x350x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x351x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x351x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x352x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x352x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x353x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x353x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x354x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x354x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x355x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x355x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x356x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x356x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x357x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x357x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x358x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x358x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x359x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x359x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x360x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x360x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x361x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x361x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x362x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x362x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x363x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x363x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x364x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x364x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x365x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x365x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x366x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x366x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x367x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x367x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x368x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x368x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x369x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x369x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x370x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x370x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x371x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x371x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x372x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x372x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x373x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x373x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x374x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x374x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x375x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x375x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x376x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x376x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x377x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x377x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x378x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x378x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x379x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x379x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x37x1x1x1x1x768x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x37x1x1x1x1x768x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x380x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x380x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x381x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x381x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x382x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x382x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x383x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x383x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x384x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x384x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x385x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x385x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x386x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x386x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x387x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x387x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x388x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x388x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x389x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x389x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x38x1x1x1x1x768x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x38x1x1x1x1x768x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x390x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x390x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x393x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x393x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x394x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x394x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x395x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x395x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x396x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x396x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x397x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x397x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x39x1x1x1x1x768x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x39x1x1x1x1x768x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x39x1x1x1x1x768x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x39x1x1x1x1x768x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x40x1x1x1x1x768x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x40x1x1x1x1x768x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x410x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x410x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x411x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x411x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x412x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x412x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x413x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x413x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x414x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x414x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x415x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x415x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x416x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x416x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x417x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x417x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x418x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x418x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x419x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x419x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x420x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x420x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x421x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x421x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x422x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x422x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x423x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x423x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x42x1x1x1x1x768x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x42x1x1x1x1x768x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x472x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x472x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x473x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x473x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x474x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x474x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x475x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x475x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x476x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x476x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x477x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x477x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x478x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x478x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x480x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x480x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x481x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x481x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x511x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x511x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x512x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x512x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x513x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x513x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x514x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x514x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x515x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x515x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x516x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x516x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x517x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x517x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x518x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x518x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x519x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x519x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x520x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x520x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x521x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x521x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x52x1x1x1x1x768x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x52x1x1x1x1x768x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x611x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x611x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x613x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x613x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x614x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x614x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x616x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x616x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x617x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x617x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x618x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x618x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x621x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x621x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x622x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x622x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x625x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x625x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x737x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x737x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x738x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x738x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x740x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x740x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x744x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x744x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x748x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x748x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x750x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x750x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x751x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x751x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x754x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x754x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x755x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x755x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x77x1x1x1x1x768x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x77x1x1x1x1x768x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x78x1x1x1x1x768x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x78x1x1x1x1x768x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x1536x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x1536x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x1536x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x1536x24x24x1x3x3x1x1536x4x1x1x0x2x2x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x256x256x1x1x1x1x3072x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1536x256x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x292x292x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x292x292x1x9x9x1x1536x4x4x4x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x30x30x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x1536x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x1536x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x1536x32x32x1x1x1x1x280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x1536x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1536x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x32x32x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x32x32x1x3x3x1x1536x1x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x32x32x1x3x3x1x1536x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x32x32x1x9x9x1x1536x4x4x4x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x37x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x3x3x1x1x5x1x1536x1x0x2x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x62x62x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x64x64x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x64x64x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x64x64x1x1x1x1x3076x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x64x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x64x64x1x2x2x1x3072x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x64x64x1x3x3x1x1536x1x1x1x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1536x64x64x1x3x3x1x1536x1x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x64x64x1x3x3x1x1536x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x64x64x1x5x5x1x1536x1x2x2x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x64x64x1x7x7x1x1536x1x3x3x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1536x64x64x1x7x7x1x1536x4x3x3x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1536x6x6x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x6x6x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x6x6x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x1x1x1x3077x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1536x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x7x7x1x3x3x1x1536x4x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x7x7x1x5x5x1x1536x1x2x2x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x7x7x1x7x7x1x1536x1x3x3x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x7x7x1x9x9x1x1536x4x4x4x0x1x1x0x1x1x0x0x1536xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1536x8x8x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x8x8x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x8x8x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x8x8x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x8x8x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1536x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1536x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1536x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1536x8x8x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1536x8x8x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1542x14x14x1x3x3x1x1542x1x1x1x0x2x2x0x1x1x0x0x1542xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x154x14x14x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1552x128x128x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1552x128x128x1x1x1x1x2304x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1552x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1552x13x13x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1552x14x14x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1552x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1552x55x55x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1552x56x56x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x155x128x128x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1560x7x7x1x1x1x1x277x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x1560x7x7x1x3x3x1x1560x4x1x1x0x1x1x0x1x1x0x0x1560xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1568x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1568x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1568x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1568x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1568x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1568x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1568x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1568x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1568x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1568x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1568x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1568x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1568x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1568x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1568x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1568x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1568x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x128x128x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x156x128x128x1x5x1x1x156x4x2x0x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x128x128x1x5x5x1x156x1x2x2x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x14x14x1x1x5x1x156x1x0x2x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x156x14x14x1x1x5x1x156x4x0x2x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x14x14x1x5x5x1x156x4x2x2x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x156x14x14x1x7x7x1x156x1x3x3x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x156x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x256x256x1x3x3x1x156x1x1x1x0x1x1x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x256x256x1x3x3x1x156x4x1x1x0x2x2x0x1x1x0x0x156xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x156x28x28x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x156x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1584x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1584x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1584x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1584x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1584x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1584x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1584x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1584x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1584x1x1x1x1x1x1x132x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x1x1x1x1x1x1x132x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x32x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x64x64x1x5x5x1x1584x1x2x2x0x1x1x0x1x1x0x0x1584xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1584x64x64x1x5x5x1x1584x4x2x2x0x1x1x0x1x1x0x0x1584xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1584x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1584x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1584x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1584x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1584x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1584x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1584x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1584x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1584x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1584x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x159x128x128x1x1x1x1x954x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x159x14x14x1x1x1x1x954x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x159x1x1x1x1x1x1x1908x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x159x64x64x1x1x1x1x954x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1600x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1600x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1600x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1600x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1600x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1600x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1600x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1600x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1600x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1600x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1600x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1600x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1600x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x1024x1024x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x160x10x10x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x10x10x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x160x112x112x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x112x112x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x126x126x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x126x126x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x160x128x128x1x1x1x1x360x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x400x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x128x128x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x128x128x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x128x128x1x5x5x1x160x1x2x2x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x128x128x1x7x7x1x320x1x3x3x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x12x12x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x12x12x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x12x12x1x3x3x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[6];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x160x12x12x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x160x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x13x25x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x13x25x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x13x25x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x13x25x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x13x25x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x13x25x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x14x14x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x160x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[10];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x160x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x1x1x1x67x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x160x14x14x1x2x2x1x304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x14x14x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x14x14x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x14x14x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x14x14x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x14x14x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x14x14x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x14x14x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x14x14x1x3x3x1x528x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x14x14x1x3x3x1x528x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[10];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x160x14x14x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x14x14x1x7x7x1x160x4x3x3x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x14x14x1x7x7x1x160x4x9x9x0x1x1x0x3x3x0x0x160xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x160x15x21x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x15x21x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x15x21x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x15x21x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x15x21x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x15x21x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x15x21x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x15x21x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x15x21x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x15x21x1x3x3x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x16x16x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x160x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[8];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x17x17x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x17x17x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x3x3x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x160x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x160x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,1,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,83[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x1x1x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x3840x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x1x1x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x21x15x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x21x15x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x160x21x15x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x21x15x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x160x21x15x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x21x15x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x21x15x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x21x15x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x21x15x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x21x15x1x3x3x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x24x24x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x256x256x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x256x256x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x256x256x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x256x256x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x256x256x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x256x256x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x256x256x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x256x256x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x256x256x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x256x256x1x5x5x1x160x1x2x2x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x25x13x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x160x25x13x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x25x13x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x160x25x13x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x25x13x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x160x25x13x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x160x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x160x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x28x28x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x28x28x1x2x2x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x2x2x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x28x28x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x28x28x1x5x5x1x160x1x2x2x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x5x5x1x160x4x2x2x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x7x7x1x160x1x3x3x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x28x28x1x7x7x1x320x1x3x3x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x32x32x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x32x32x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x32x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x32x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x32x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x160x32x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x32x32x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x32x32x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x32x32x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x32x32x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x32x32x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x32x32x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x32x32x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x32x32x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x384x384x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x160x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x4x16384x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x4x196x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x512x512x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x512x512x1x1x1x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x3x3x1x160x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x512x512x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x512x512x1x5x5x1x160x1x2x2x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x160x512x512x1x5x5x1x160x4x2x2x0x2x2x0x1x1x0x0x160xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x160x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x160x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x56x56x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x56x56x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x160x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x160x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x64x128x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x64x128x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x64x128x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x64x64x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x64x64x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x64x64x1x1x1x1x328x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x64x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x64x64x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x64x64x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x160x65x65x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x73x73x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+2
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x160x7x7x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x160x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x160x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x7x7x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x160x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x160x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x160x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x160x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x7x7x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x160x7x7x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x160x7x7x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x160x7x7x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x160x7x7x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x160x7x7x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x160x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x160x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x160x8x8x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x8x8x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x160x8x8x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1624x64x64x1x3x3x1x1624x1x1x1x0x2x2x0x1x1x0x0x29xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1624x7x7x1x1x1x1x1624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x162x1x1x1x1x1x1x1944x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x162x512x512x1x1x1x1x38x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x162x64x64x1x1x1x1x972x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x162x7x7x1x1x1x1x972x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x162x7x7x1x1x1x1x972x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x12x12x1x3x3x1x1632x1x1x1x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1632x12x12x1x3x3x1x1632x4x1x1x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x12x12x1x5x5x1x1632x1x2x2x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x12x12x1x5x5x1x1632x4x2x2x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1632x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1632x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1632x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x16x16x1x1x1x1x272x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1632x16x16x1x1x1x1x272x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x16x16x1x1x1x1x272x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x1632x16x16x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1632x16x16x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x16x16x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1632x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1632x1x1x1x1x1x1x68x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x1632x1x1x1x1x1x1x68x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x1x1x1x1x1x1x68x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[9];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1632x1x1x1x1x1x1x68x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x1632x1x1x1x1x1x1x68x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x1x1x1x1x1x1x68x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x1632x32x32x1x5x5x1x1632x1x2x2x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x64x64x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x64x64x1x3x3x1x1632x4x1x1x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x64x64x1x5x5x1x1632x1x2x2x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1632x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1632x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1632x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1632x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1632x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1632x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1632x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1632x7x7x1x3x3x1x1632x1x1x1x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1632x7x7x1x3x3x1x1632x4x1x1x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1632x7x7x1x5x5x1x1632x4x2x2x0x1x1x0x1x1x0x0x1632xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x164x128x128x1x3x3x1x164x1x1x1x0x1x1x0x1x1x0x0x164xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x164x14x14x1x1x1x1x74x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1664x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x128x128x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1664x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1664x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1664x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1664x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1664x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1664x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1664x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1664x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,77[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1664x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1664x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1664x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1664x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1664x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1664x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x166x128x128x1x1x1x1x332x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x166x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x166x514x514x1x3x3x1x166x1x0x0x0x2x2x0x1x1x0x0x166xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x166x514x514x1x3x3x1x166x4x0x0x0x2x2x0x1x1x0x0x166xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x166x64x64x1x1x1x1x1328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x167x14x14x1x1x1x1x1002x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1680x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1680x128x128x1x3x3x1x1680x1x1x1x0x2x2x0x1x1x0x0x1680xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1680x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1680x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1680x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1680x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1680x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1680x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1680x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1680x1x1x1x1x1x1x140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x1x1x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x64x64x1x3x3x1x1680x1x1x1x0x2x2x0x1x1x0x0x1680xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1680x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1680x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1680x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1680x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1680x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1680x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1680x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1680x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1680x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1680x7x7x1x3x3x1x1680x4x1x1x0x1x1x0x1x1x0x0x1680xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x168x128x128x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x168x128x128x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x168x128x128x1x1x1x1x504x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x168x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x168x14x14x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x168x1x1x1x1x1x1x42x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x21x21x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x168x21x21x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x168x256x256x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x168x256x256x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x168x256x256x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x168x256x256x1x1x1x1x408x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x168x256x256x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x256x256x1x3x3x1x168x1x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x168x256x256x1x3x3x1x168x4x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x256x256x1x5x5x1x168x1x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x1x1x1x408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x168x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x168x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x168x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x168x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x168x28x28x1x1x1x1x84x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x3x3x1x168x4x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x16x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x32x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x28x28x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x168x42x42x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x168x42x42x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x168x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x168x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x168x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x168x42x42x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x168x42x42x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x168x42x42x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x168x42x42x1x3x3x1x168x64x1x1x0x1x1x0x1x1x0x0x168xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x168x42x42x1x3x3x1x168x64x1x1x0x1x1x0x1x1x0x0x168xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x42x42x1x3x3x1x168x64x1x1x0x1x1x0x1x1x0x0x168xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x168x42x42x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xB=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x168x42x42x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x42x42x1x5x5x1x168x64x2x2x0x1x1x0x1x1x0x0x168xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x168x512x512x1x1x1x1x392x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x168x512x512x1x3x3x1x168x1x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x168x56x56x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x168x56x56x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x168x56x56x1x1x1x1x84x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x168x56x56x1x3x3x1x168x4x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x168x64x64x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x168x64x64x1x1x1x1x504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x168x64x64x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x64x64x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x168x64x64x1x5x5x1x168x1x2x2x0x2x2x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x7x7x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x168x7x7x1x9x9x1x168x1x4x4x0x1x1x0x1x1x0x0x168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x168x83x83x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1696x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1696x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1696x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1696x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1696x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1696x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1696x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1696x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1696x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1696x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1696x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1696x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1696x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1696x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1696x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x1024x1024x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x1024x1024x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187
2x16x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x16x1024x1024x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187
2x16x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15
2x16x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x16x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x16x1024x1024x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x16x10x10x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x112x112x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x16x112x112x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x112x112x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x112x112x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x16x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x112x112x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x112x112x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x112x112x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x16x112x112x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x16x112x112x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x112x112x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x112x112x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x112x112x1x4x4x1x96x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x113x113x1x2x2x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x120x120x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x120x120x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x128x128x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x128x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x128x128x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x16x130x130x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x130x130x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x130x130x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x16x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x16x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x16x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x16x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x16x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x16x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x16x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x16x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x16x14x14x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x14x14x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x14x14x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x14x14x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x14x14x1x5x5x1x6x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x16x14x14x1x5x5x1x6x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x16x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187
2x16x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15
2x16x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187
2x16x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x16x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x16x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x16x16x16x1x2x2x1x1920x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x16x16x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x16x16x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x16x16x1x3x3x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x16x16x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x16x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x1920x1080x1x3x3x1x4x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x1920x1080x1x3x3x1x4x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x1920x1080x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x192x192x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x1x1x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x1x1x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x1x1x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x1x1x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x1x1x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x1x1x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x1x1x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x16x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x16x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x16x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187
2x16x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x16x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x16x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79
2x16x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x16x2048x2048x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x16x224x224x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x225x225x1x2x2x1x4x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x225x225x1x2x2x1x4x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x16x225x225x1x2x2x1x4x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x225x225x1x2x2x1x4x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x225x225x1x2x2x1x4x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x225x225x1x2x2x1x4x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x2x2x1x4x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x240x135x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x24x240x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x24x240x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x24x240x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x24x240x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x24x240x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x24x240x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x24x240x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x24x240x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x16x256x256x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x256x256x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x256x256x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x256x256x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x256x256x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x256x256x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x256x256x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x256x256x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x256x256x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x256x256x1x5x5x1x16x1x2x2x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x256x256x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x16x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x16x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x16x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x16x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x16x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x16x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x28x28x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x16x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x3x3x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x16x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x2x2x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x2x2x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
2x16x2x2x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x2x2x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x16x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x16x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x16x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x16x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x16x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x16x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x16x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x16x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195
2x16x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91
2x16x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x16x30x30x1x3x3x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x30x30x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x32x32x1x2x2x1x1920x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x32x32x1x2x2x1x3072x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x32x32x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x16x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x16x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x16x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x480x270x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x480x270x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x16x48x480x1x3x3x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x4x4x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x16x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x16x512x512x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x16x512x512x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x16x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x512x512x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x512x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x512x512x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x16x512x512x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x512x512x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x512x512x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x512x512x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x512x512x1x5x5x1x16x1x2x2x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x16x512x512x1x5x5x1x16x4x2x2x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x513x513x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x16x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x54x54x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x54x54x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,43;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x16x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x16x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x16x55x55x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x55x55x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x55x55x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x55x55x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x55x55x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x16x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x16x56x56x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x56x56x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x56x56x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x16x56x56x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x16x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x16x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x64x128x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x64x64x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x16x6x6x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x16x7x7x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x7x7x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x16x80x80x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x16x8x8x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x16x8x8x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x16x8x8x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x16x8x8x1x7x7x1x2x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x16x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x16x960x540x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x16x960x540x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x1704x128x128x1x1x1x1x318x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1704x128x128x1x3x3x1x1704x1x1x1x0x1x1x0x1x1x0x0x1704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1704x128x128x1x3x3x1x1704x4x1x1x0x1x1x0x1x1x0x0x1704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x171x128x128x1x1x1x1x125x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x171x14x14x1x1x1x1x818x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x171x256x256x1x1x1x1x198x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x128x128x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x128x128x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x128x128x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x128x128x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1728x128x128x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,77[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1728x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1728x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1728x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x14x14x1x3x3x1x1728x1x1x1x0x1x1x0x1x1x0x0x1728xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1728x1x1x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x1x1x1x1x1x1x1984x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1728x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x1728x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1728x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x1728x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x1728x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x1728x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x1728x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1728x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1728x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x1728x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1728x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x1728x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x1728x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x1728x64x64x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x64x64x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x64x64x1x5x5x1x1728x4x2x2x0x1x1x0x1x1x0x0x1728xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1728x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1728x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1728x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1728x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1728x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1728x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1728x7x7x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x174x64x64x1x1x1x1x1044x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x175x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x175x1x1x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x175x257x257x1x3x3x1x175x1x0x0x0x2x2x0x1x1x0x0x175xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x175x257x257x1x3x3x1x175x4x0x0x0x2x2x0x1x1x0x0x175xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1760x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1760x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1760x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1760x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1760x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1760x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1760x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1760x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1760x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x176x111x111x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x111x111x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x111x111x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x112x112x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x112x112x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x112x112x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x113x113x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x113x113x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x113x113x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x128x128x1x1x1x1x44x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x176x128x128x1x1x1x1x44x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x176x128x128x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x176x128x128x1x3x3x1x352x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x176x128x128x1x3x3x1x352x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x13x13x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x176x14x14x1x1x1x1x1408x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x176x14x14x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x176x14x14x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x176x14x14x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x176x14x14x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,18[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x176x14x14x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x14x14x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x176x14x14x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x1x1x1x44x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x3x3x1x176x10x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x10x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x176x14x14x1x3x3x1x176x10x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x10x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x10x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x10x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x176x14x14x1x3x3x1x176x10x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x10x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x14x14x1x3x3x1x176x11x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x11x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x11x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x11x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x11x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x11x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x176x14x14x1x3x3x1x176x11x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x11x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x128x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x16x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x16x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x16x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x16x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x16x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x20x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x20x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x176x14x14x1x3x3x1x176x20x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x20x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x14x14x1x3x3x1x176x20x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x20x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x20x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x20x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x32x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x176x14x14x1x3x3x1x176x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x64x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x176x14x14x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x176x14x14x1x3x3x1x176x8x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x8x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x14x14x1x3x3x1x176x8x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x176x14x14x1x3x3x1x176x8x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x176x14x14x1x3x3x1x176x8x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x176x1x1x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x176x256x256x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x176x27x27x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x27x27x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x176x28x28x1x1x1x1x176x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x176x28x28x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x176x28x28x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x28x28x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x176x28x28x1x1x1x1x176x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x176x28x28x1x1x1x1x176x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x176x28x28x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x176x28x28x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x28x28x1x1x1x1x176x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x176x28x28x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x128x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x22x1x1x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x32x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x64x0x0x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x28x28x1x3x3x1x176x8x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x32x32x1x1x1x1x1064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x176x32x32x1x3x3x1x176x1x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x176x56x56x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x56x56x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x176x56x56x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x56x56x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x56x56x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x56x56x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x57x57x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x57x57x1x3x3x1x176x128x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x176x57x57x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x57x57x1x3x3x1x176x32x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x57x57x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xB=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x176x57x57x1x3x3x1x176x64x1x1x0x2x2x0x1x1x0x0x176xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x176x64x64x1x1x1x1x1064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x176x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x7x7x1x1x1x1x532x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x7x7x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x176x7x7x1x3x3x1x176x1x1x1x0x1x1x0x1x1x0x0x176xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1776x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1776x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1776x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1776x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1776x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1776x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1776x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1776x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1776x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1776x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1776x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1776x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1776x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1776x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1776x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1776x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1792x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x128x128x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1792x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1792x14x14x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1792x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1792x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x14x14x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1792x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x1792x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1792x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x14x14x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1792x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x1792x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x1792x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x1792x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x1792x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x64x64x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1792x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1792x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1792x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1792x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1792x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1792x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1792x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1792x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x17x56x56x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x17x56x56x1x1x1x1x69x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x180x128x128x1x3x3x1x180x1x1x1x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x128x128x1x5x5x1x180x4x2x2x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x129x129x1x3x3x1x180x1x0x0x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x131x131x1x5x5x1x180x1x0x0x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x180x14x14x1x7x7x1x180x4x3x3x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x180x14x14x1x9x9x1x180x1x4x4x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x180x15x15x1x3x3x1x180x4x0x0x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x180x17x17x1x5x5x1x180x1x0x0x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x180x17x17x1x5x5x1x180x4x0x0x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x180x1x1x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x180x256x256x1x3x3x1x180x4x1x1x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x28x28x1x3x3x1x180x1x1x1x0x1x1x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x28x28x1x3x3x1x180x4x1x1x0x1x1x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x28x28x1x3x3x1x180x4x1x1x0x2x2x0x1x1x0x0x180xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x180x64x64x1x1x1x1x1076x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1812x32x32x1x1x1x1x324x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x181x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1824x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1824x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1824x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1824x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1824x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1824x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1824x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1824x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x15x15x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x32x32x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x32x32x1x5x5x1x1824x1x2x2x0x1x1x0x1x1x0x0x1824xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1824x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1824x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1824x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1824x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1824x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1824x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1824x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1824x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1824x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1824x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1824x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1824x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1824x7x7x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x328x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1824x7x7x1x5x5x1x1824x1x2x2x0x1x1x0x1x1x0x0x1824xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x182x64x64x1x1x1x1x1092x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x183x128x128x1x1x1x1x1098x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x184x128x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x184x128x128x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x184x128x128x1x3x3x1x184x1x1x1x0x1x1x0x1x1x0x0x23xNCHWxFP16xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x184x128x128x1x3x3x1x184x4x1x1x0x1x1x0x1x1x0x0x184xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x184x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x184x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x184x14x14x1x3x3x1x184x1x1x1x0x1x1x0x1x1x0x0x184xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x184x1x1x1x1x1x1x360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x184x1x1x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x184x64x64x1x1x1x1x736x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x184x64x64x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x184x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x184x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x184x7x7x1x1x5x1x184x4x0x2x0x1x1x0x1x1x0x0x184xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1856x14x14x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x64x64x1x5x5x1x1856x4x2x2x0x1x1x0x1x1x0x0x1856xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1856x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1856x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1856x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1856x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1856x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,18[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1856x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1856x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1856x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1856x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1856x7x7x1x5x5x1x1856x4x2x2x0x1x1x0x1x1x0x0x1856xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x185x64x64x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1872x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1872x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1872x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1872x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1872x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1872x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1872x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1872x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1872x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1872x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1872x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1872x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x1872x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1872x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1872x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1872x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1872x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1872x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1872x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1872x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1888x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x28x28x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x28x28x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1888x32x32x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1888x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1888x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1888x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1888x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1888x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1888x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1888x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1888x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1888x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1888x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1888x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1888x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x188x1x1x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x18x14x14x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x18x1x1x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x18x256x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x18x256x256x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x18x512x512x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x18x512x512x1x3x3x1x18x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x18x56x56x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x18x56x56x1x3x3x1x18x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x1908x128x128x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1908x1x1x1x1x1x1x159x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x190x64x64x1x1x1x1x1140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1912x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1912x64x64x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1912x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x191x128x128x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x191x64x64x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1920x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x128x128x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x128x128x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1920x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1920x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1920x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x3x3x1x1920x1x1x1x0x1x1x0x1x1x0x0x1920xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1920x14x14x1x3x3x1x1920x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x14x14x1x3x3x1x1920x1x1x1x0x2x2x0x1x1x0x0x1920xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1920x14x14x1x3x3x1x1920x4x1x1x0x1x1x0x1x1x0x0x1920xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1920x14x14x1x3x3x1x1920x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x16x16x1x1x1x1x1280x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x16x16x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:158
2x1920x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1920x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x16x16x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x16x16x1x3x3x1x640x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1920x16x16x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x1x1x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x1x1x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x20x20x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x20x20x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x20x20x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x24x24x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x24x24x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x24x24x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x24x24x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x24x24x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x32x32x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:168
2x1920x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1920x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x40x40x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x48x48x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x48x48x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x4x4x1x1x1x1x1280x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x64x64x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x64x64x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1920x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1920x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1920x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1920x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1920x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x1x1x1x960x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x8x8x1x1x1x1x960x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1920x8x8x1x3x3x1x1920x4x1x1x0x1x1x0x1x1x0x0x1920xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x1920x8x8x1x3x3x1x960x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1920x8x8x1x3x3x1x960x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1920x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1024x1024x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1025x1025x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x112x112x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x112x112x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x112x112x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x112x112x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x113x113x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x113x113x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x113x113x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x113x113x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x125x125x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x125x125x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x126x126x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x128x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x128x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x128x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x128x128x1x1x1x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x128x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x128x128x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x128x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x128x128x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x128x128x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x128x1x5x5x1x192x4x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x128x128x1x9x9x1x192x4x4x4x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x128x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x128x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x128x256x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x128x256x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x128x256x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[7];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x12x12x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x12x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[5];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x12x12x1x7x7x1x192x1x3x3x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x192x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x12x8x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x12x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x12x8x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x12x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x12x8x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x12x8x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x12x8x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x12x8x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x12x8x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x12x8x1x2x2x1x128x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x2x2x1x128x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x12x8x1x2x2x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x12x8x1x2x2x1x128x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x2x2x1x128x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x12x8x1x2x2x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x12x8x1x2x2x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x12x8x1x2x2x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x2x2x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x12x8x1x2x2x1x128x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x12x8x1x2x2x1x128x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x12x8x1x2x2x1x128x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x12x8x1x2x2x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x12x8x1x2x2x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x12x8x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x12x8x1x2x2x1x128x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x12x8x1x2x2x1x128x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x12x8x1x2x2x1x128x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x132x132x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,10,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x13x13x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x13x13x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x192x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x13x13x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x192x13x13x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x13x13x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,5,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x192x13x13x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x13x13x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x13x13x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x13x13x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x25x1x3x3x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x13x25x1x3x3x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x13x25x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x13x25x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x13x25x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x13x25x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x25x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x13x25x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x25x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x13x25x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x13x25x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x13x25x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x13x25x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x13x25x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x141x141x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x141x141x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x141x141x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x141x141x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x141x141x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x141x141x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x141x141x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x141x141x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x141x141x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x141x141x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x141x141x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x141x141x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8]
2x192x142x142x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10]
2x192x142x142x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x142x142x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x142x142x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x142x142x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x142x142x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x145x145x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x147x147x1x2x2x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1008x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1280x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[4];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x14x14x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x14x14x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x192x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x14x14x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x14x14x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x816x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x816x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x864x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x14x14x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x912x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x192x14x14x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x14x14x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x1x5x1x192x1x0x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x192x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x192x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x192x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x14x14x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x14x14x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x14x14x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x192x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x14x14x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x14x14x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x14x14x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x14x14x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x14x14x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x14x14x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x192x14x14x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x192x14x14x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x5x5x1x192x4x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x14x14x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x192x14x14x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x14x14x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x14x14x1x7x7x1x192x4x3x3x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x14x14x1x7x7x1x384x4x3x3x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x14x14x1x9x9x1x384x4x4x4x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x192x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x15x15x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x15x15x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x15x15x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x15x15x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x15x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x15x15x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x15x15x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x15x15x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x15x15x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x15x15x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x15x1x3x3x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x15x21x1x3x3x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x21x1x3x3x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x15x21x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x15x21x1x3x3x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x15x21x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x15x21x1x3x3x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x15x21x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x15x21x1x3x3x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x15x21x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x15x21x1x3x3x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x15x21x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x15x21x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x16x16x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x16x16x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x16x16x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x16x16x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x16x16x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x192x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x17x17x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x1x7x1x128x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x1x7x1x128x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x1x7x1x128x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x128x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x128x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x1x7x1x128x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x128x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x1x7x1x160x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x192x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x1x7x1x160x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x192x17x17x1x1x7x1x160x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x1x7x1x160x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x1x7x1x160x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x160x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x1024x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[7];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x84x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x1x7x1x192x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x224x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x1x7x1x224x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x192x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x17x17x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x17x17x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x3x3x1x320x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x3x3x1x320x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x3x3x1x320x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x3x3x1x768x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x128x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x192x17x17x1x7x1x1x128x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x17x17x1x7x1x1x128x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x7x1x1x128x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x128x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x7x1x1x128x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x17x17x1x7x1x1x128x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x128x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x160x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x7x1x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x192x17x17x1x7x1x1x160x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x7x1x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x17x17x1x7x1x1x160x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x160x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x1024x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x17x17x1x7x1x1x192x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x17x17x1x7x1x1x224x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x192x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x224x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x224x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x17x17x1x7x1x1x224x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x17x17x1x7x1x1x224x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x17x17x1x7x1x1x224x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x17x17x1x7x1x1x224x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x192x192x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x192x192x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x1x1x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x1x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x192x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x192x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+2
2x192x1x21x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x1x21x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x1x21x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x21x15x1x3x3x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x21x15x1x3x3x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x21x15x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x21x15x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x21x15x1x3x3x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x21x15x1x3x3x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x21x15x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x21x15x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x21x15x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x21x15x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x21x15x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x21x15x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x21x15x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x21x15x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x21x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x21x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x21x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+2
2x192x21x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x21x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x21x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x21x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x21x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x21x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x21x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x21x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x21x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x21x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x21x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x21x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x223x223x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x223x223x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x224x224x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x224x224x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x225x225x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x225x225x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x23x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+2
2x192x23x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x192x23x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x23x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x192x23x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x23x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x23x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x23x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x23x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x23x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x23x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x192x23x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x23x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x23x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x23x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x23x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x23x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x24x16x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x48x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x48x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x24x16x1x1x1x1x48x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x24x16x1x1x1x1x48x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x48x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x24x16x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x24x16x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x48x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x48x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x48x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x48x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x24x16x1x1x1x1x48x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x48x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x48x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x48x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x48x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x48x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x24x16x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x48x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x48x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x48x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x48x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x48x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x48x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x192x24x16x1x1x1x1x48x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x24x16x1x1x1x1x48x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x48x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x24x16x1x1x1x1x48x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x24x16x1x1x1x1x48x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x24x16x1x1x1x1x48x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x48x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x48x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x24x16x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x24x16x1x1x1x1x48x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x48x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x48x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x64x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x64x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x24x16x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x24x16x1x1x1x1x64x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x24x16x1x1x1x1x64x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x64x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x64x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x24x16x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x64x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x64x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x24x16x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x64x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x64x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x64x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x24x16x1x1x1x1x64x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x1x1x1x64x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x24x16x1x1x1x1x64x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x1x1x1x64x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x24x16x1x1x1x1x64x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x64x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x24x16x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x24x16x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x24x16x1x2x2x1x96x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x24x16x1x2x2x1x96x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x2x2x1x96x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x24x16x1x2x2x1x96x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x192x24x16x1x2x2x1x96x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x24x16x1x2x2x1x96x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x24x16x1x2x2x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x2x2x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x24x16x1x2x2x1x96x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x24x16x1x2x2x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x24x16x1x2x2x1x96x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x24x16x1x2x2x1x96x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x24x16x1x2x2x1x96x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x24x16x1x3x3x1x194x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x192x24x16x1x3x3x1x194x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x24x16x1x3x3x1x194x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x192x24x16x1x3x3x1x194x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x192x24x16x1x3x3x1x194x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x24x16x1x3x3x1x194x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x192x24x16x1x3x3x1x194x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x192x24x16x1x3x3x1x194x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x24x16x1x3x3x1x194x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x24x16x1x3x3x1x194x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x24x16x1x3x3x1x194x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x24x16x1x3x3x1x194x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x252x252x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x253x253x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x253x253x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x253x253x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x253x253x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x256x256x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x387x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x256x256x1x1x1x1x387x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x256x256x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x432x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x192x256x256x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x256x256x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x256x256x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x256x256x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x256x256x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x256x256x1x7x7x1x192x1x3x3x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x256x256x1x9x9x1x192x1x4x4x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x256x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x256x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x256x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x256x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x256x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x257x257x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x259x259x1x5x5x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x25x13x1x3x3x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x25x13x1x3x3x1x128x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x25x13x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x25x13x1x3x3x1x128x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x25x13x1x3x3x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x25x13x1x3x3x1x128x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x25x13x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x25x13x1x3x3x1x160x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x25x13x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x25x13x1x3x3x1x160x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x25x13x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x25x13x1x3x3x1x160x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x25x13x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x192x25x13x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x25x13x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x25x13x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x25x1x1x3x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x25x1x1x3x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x3x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x25x1x1x4x1x1x4x10x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x192x25x1x1x4x1x1x4x11x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x12x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x13x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x14x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x25x1x1x4x1x1x4x15x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x16x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x17x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x18x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x19x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x1x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Default, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+-1
2x192x25x1x1x4x1x1x4x20x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x21x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x22x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x23x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x24x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x25x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x26x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x27x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x28x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x29x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x2x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x192x25x1x1x4x1x1x4x30x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x192x25x1x1x4x1x1x4x31x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x32x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x192x25x1x1x4x1x1x4x33x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x192x25x1x1x4x1x1x4x34x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x192x25x1x1x4x1x1x4x35x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x192x25x1x1x4x1x1x4x36x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x192x25x1x1x4x1x1x4x37x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+32
2x192x25x1x1x4x1x1x4x3x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Default, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+1
2x192x25x1x1x4x1x1x4x4x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x192x25x1x1x4x1x1x4x5x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x192x25x1x1x4x1x1x4x6x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x192x25x1x1x4x1x1x4x7x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x192x25x1x1x4x1x1x4x8x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x192x25x1x1x4x1x1x4x9x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x192x25x25x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x26x26x1x3x3x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x26x26x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x26x26x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x26x26x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x26x26x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x27x27x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x27x27x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x27x27x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x27x27x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x27x27x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x27x27x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x192x27x27x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x192x27x27x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x27x27x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x27x27x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x27x27x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x27x27x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x192x27x27x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x27x27x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[6];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x27x27x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x27x27x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x27x27x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x27x27x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x192x27x27x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x27x27x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[10];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x27x27x1x5x5x1x64x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x192x27x27x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[9];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x27x27x1x5x5x1x64x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:48
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x192x27x27x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x27x27x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x27x27x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x27x27x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x283x283x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x283x283x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x284x284x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x285x285x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,74[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,165[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x388x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x28x28x1x1x1x1x432x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x432x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x432x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x28x28x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x544x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x624x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+32
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x192x28x28x1x1x1x1x624x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x28x28x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x624x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x192x28x28x1x1x1x1x624x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x624x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x624x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x640x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:138
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x720x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x2x2x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x2x2x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x2x2x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x2x2x1x384x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x2x2x1x384x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x2x2x1x768x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x2x2x1x768x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x2x2x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x2x2x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x192x28x28x1x2x2x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x2x2x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x192x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x192x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x192x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x28x28x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x28x28x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x28x28x1x3x3x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x28x28x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x11x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x11x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x28x28x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x28x28x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x28x28x1x3x3x1x192x21x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x21x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x22x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x28x28x1x3x3x1x192x22x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x192x28x28x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x28x28x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x352x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x28x28x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x464x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x192x28x28x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x192x28x28x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x98x1x1x0x1x1x0x1x1x0x0x192xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x192x98x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x192x28x28x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x3x3x1x384x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x384x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x28x28x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x28x28x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x28x28x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x4x4x1x192x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x192x16x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x192x32x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x192x64x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x28x28x1x5x5x1x32x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x29x29x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x29x29x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x29x29x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x29x29x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x192x29x29x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x29x29x1x3x3x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x29x29x1x3x3x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x29x29x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x29x29x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x29x29x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x29x29x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x300x300x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x301x301x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x31x31x1x3x3x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x31x31x1x3x3x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x31x31x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x31x31x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x31x31x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x31x31x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x32x32x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x32x32x1x1x1x1x512x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x32x32x1x1x1x1x806x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x32x32x1x7x7x1x384x1x3x3x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x32x32x1x8x8x1x3x1x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x192x32x32x1x8x8x1x3x1x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x32x32x1x8x8x1x3x28x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x192x32x32x1x8x8x1x3x28x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x33x33x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x33x33x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x33x33x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x33x33x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x33x33x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x33x33x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x33x33x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x33x33x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x192x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x33x33x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x33x33x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x34x34x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6]
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x34x34x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x34x34x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x34x34x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x35x35x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x48x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x35x35x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x35x35x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x35x35x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x35x35x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x35x35x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x35x35x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x35x35x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x35x35x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x35x35x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x35x35x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x35x35x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x35x35x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x35x35x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x35x35x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x35x35x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x35x35x1x3x3x1x224x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x35x35x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x35x35x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x192x35x35x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x192x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x35x35x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x36x36x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x36x36x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x36x36x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x36x36x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x36x36x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x37x37x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x192x40x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x40x60x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x40x60x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x48x48x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x48x48x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x48x48x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x4x16384x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x4x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x4x196x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x4x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x4x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x4x256x1x1x1x1x385x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x4x4096x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x192x4x4096x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x4x49x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x192x4x4x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x4x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x4x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x4x64x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x4x64x1x1x1x1x385x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x4x64x1x1x1x1x385x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x508x508x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x508x508x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x512x512x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x512x512x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x1x1x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x512x512x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x512x512x1x1x1x1x389x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x512x512x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x192x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250
2x192x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x512x512x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x512x512x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x512x512x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x512x512x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x512x512x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x512x512x1x9x9x1x192x4x4x4x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x515x515x1x5x5x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x52x52x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x55x55x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x55x55x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x336x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x56x56x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x336x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x56x56x1x1x1x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x56x56x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x389x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x56x56x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x192x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x192x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x192x56x56x1x2x2x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x56x56x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x56x56x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x56x56x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,7,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x192x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:13
2x192x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x192x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x192x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x56x56x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x56x56x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x192x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x56x56x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x56x56x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x56x56x1x7x7x1x192x4x3x3x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x57x57x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x57x57x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x192x58x58x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x58x58x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x59x59x1x5x5x1x192x4x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x62x62x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x64x128x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x64x128x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x64x128x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x64x64x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x64x64x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x64x64x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x64x64x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x64x64x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x64x64x1x1x1x1x806x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x64x64x1x1x1x1x806x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x64x64x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x64x64x1x1x1x1x891x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x64x64x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x64x64x1x1x1x1x990x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x192x64x64x1x1x5x1x192x1x0x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x64x64x1x2x2x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x64x64x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x64x64x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x64x64x1x5x1x1x192x1x2x0x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x64x64x1x5x5x1x192x1x2x2x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x65x65x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x67x67x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x67x67x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x67x67x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x67x67x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x67x67x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x67x67x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x67x67x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x67x67x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x67x67x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x68x68x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x68x68x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x68x68x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x68x68x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x68x68x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x68x68x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x68x68x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x68x68x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x68x68x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x69x69x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x69x69x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x69x69x1x3x3x1x320x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x69x69x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9]
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x69x69x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x69x69x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x69x69x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+128
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x69x69x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x69x69x1x3x3x1x80x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x69x69x1x3x3x1x80x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x69x69x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x6x6x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x70x70x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x70x70x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x70x70x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x70x70x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x70x70x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x70x70x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x70x70x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x70x70x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x70x70x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x70x70x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x71x71x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x192x71x71x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x71x71x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x71x71x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x71x71x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9]
2x192x71x71x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x71x71x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x71x71x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x71x71x1x3x3x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x71x71x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x71x71x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x71x71x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x71x71x1x3x3x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x71x71x1x3x3x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x192x71x71x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x71x71x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x71x71x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x71x71x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+128
2x192x71x71x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x192x71x71x1x3x3x1x80x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x71x71x1x3x3x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x73x73x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x73x73x1x3x3x1x80x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x73x73x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x73x73x1x3x3x1x80x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+128
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x73x73x1x3x3x1x80x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x75x75x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x75x75x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x75x75x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[5];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1104x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1104x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1200x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1200x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1200x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1200x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[10];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1248x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1248x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[9];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1296x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1344x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1344x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1344x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1392x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1392x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1440x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1440x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1488x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1488x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1584x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1584x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,52;ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1632x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1680x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+16
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1680x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[9];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,48;ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1776x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1776x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1776x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1776x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1776x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1776x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1824x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1824x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1824x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1872x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1872x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1920x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[5];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2064x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[7];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x1x1x1x2160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x2160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x7x7x1x1x1x1x798x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x798x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x192x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x1x1x1x990x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x1x1x1x990x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x192x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x192x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x7x7x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x192x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x192x7x7x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x7x7x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x7x7x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x7x7x1x7x7x1x192x4x3x3x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x7x7x1x9x9x1x192x1x4x4x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x192x7x7x1x9x9x1x192x4x4x4x0x1x1x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x8x8x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x192x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x192x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x192x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x192x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x192x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x192x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x192x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,2,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x192x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x192x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x192x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x192x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x8x8x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x192x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x95x95x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x96x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x96x64x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x96x64x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x96x64x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x96x64x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x64x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x192x96x96x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x96x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x192x96x96x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x192x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x192x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x192x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x192x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x192x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x192x9x9x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x9x9x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x192x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x193x128x128x1x1x1x1x1158x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x194x24x16x1x3x3x1x192x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x194x24x16x1x3x3x1x192x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1952x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x128x128x1x3x3x1x1968x1x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1968x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1968x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1968x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1968x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1968x14x14x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x14x14x1x1x1x1x4920x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x3x3x1x1968x4x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x256x256x1x3x3x1x1968x4x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x32x32x1x3x3x1x1968x1x1x1x0x1x1x0x1x1x0x0x1968xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x1968x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x64x64x1x1x1x1x328x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1968x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x1968x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x1968x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1968x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1968x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1968x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1968x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x1968x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x1968x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x196x128x128x1x3x3x1x196x1x1x1x0x1x1x0x1x1x0x0x196xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x196x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x196x14x14x1x3x3x1x196x1x1x1x0x1x1x0x1x1x0x0x196xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x196x14x14x1x5x5x1x196x4x2x2x0x2x2x0x1x1x0x0x196xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x196x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x196x64x64x1x1x1x1x1176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x1984x128x128x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1984x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x1984x64x64x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x198x28x28x1x3x3x1x126x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x19x128x128x1x1x1x1x171x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x128x256x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x19x128x256x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x19x129x257x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x19x129x257x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x19x1x1x1x1x1x1x228x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x256x512x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x258x514x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x32x64x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x19x32x64x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x19x32x64x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x19x32x64x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x19x33x65x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x19x33x65x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x19x33x65x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x19x33x65x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x19x56x56x1x1x1x1x52x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x19x64x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x19x64x128x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x64x128x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x19x66x130x1x4x4x1x19x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x1003x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1003x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1009x80x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1009x80x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1018x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1018x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1018x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1018x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1019x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1019x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1026x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1026x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1032x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1032x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1046x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1046x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1046x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1046x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1052x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1052x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1059x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1059x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1074x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1074x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1082x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1082x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1089x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1089x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1094x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1094x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x10x10x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x10x10x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x10x10x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x10x10x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x10x10x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,1,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x10x10x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x10x10x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x1100x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1100x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1100x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1100x80x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1108x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1108x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1122x80x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1134x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1134x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1143x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1143x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1157x80x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1160x80x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1168x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1168x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1187x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1187x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1188x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1188x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1219x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1219x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1223x80x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1226x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1226x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1246x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1246x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1248x80x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1248x80x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1262x80x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1262x80x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1265x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1265x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1284x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1284x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1286x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1286x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1287x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1287x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x128x100x1x16x16x1x768x4x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x192x6x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x192x8x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x384x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x768x1x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x768x1x0x0x0x12x12x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x1024x1x16x16x1x768x6x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x128x128x1x16x16x1x768x1x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x128x1x16x16x1x768x6x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x128x2048x1x16x16x1x768x4x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x128x256x1x16x16x1x768x8x0x0x0x10x10x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1290x80x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1290x80x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1300x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1300x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1311x80x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1311x80x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1321x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1321x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1325x80x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1333x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1333x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1348x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1348x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1350x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1350x80x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1353x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1353x80x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1354x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1354x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1388x80x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1401x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1401x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x140x80x1x3x3x1x256x329x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1417x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1417x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1433x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1433x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1446x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1446x80x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1448x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1450x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1450x80x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1455x80x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1464x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1464x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1478x80x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1492x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1506x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1520x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x1520x80x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1530x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x1536x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1539x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1571x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x157x681x1x5x20x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x1x157x681x1x5x20x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x157x682x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x157x682x1x5x20x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x157x682x1x5x20x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x158x682x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x158x682x1x5x20x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x158x682x1x5x20x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x697x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x697x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x697x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x697x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x697x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x697x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x698x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x698x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x698x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x698x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x698x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x159x698x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x698x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x698x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x159x698x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x1609x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x160x698x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x160x698x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x160x698x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x160x698x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x699x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x699x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x699x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1024x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x512x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1024x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x512x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x161x700x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x161x700x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x1630x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1637x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x163x701x1x5x5x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x163x701x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x163x701x1x5x5x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x163x701x1x5x5x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x164x80x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x164x80x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1666x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1666x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1667x80x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1682x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1711x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1711x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1713x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1748x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1748x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1750x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,1,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x1760x1760x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x1815x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1815x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1821x80x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1837x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1837x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x184x80x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x184x80x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1851x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1851x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1856x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1865x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1865x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1876x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1876x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1883x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x1891x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1891x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1891x80x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1945x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1947x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1947x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1948x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1948x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1953x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1963x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1968x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1977x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1979x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x1991x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128;TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:218
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64;TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:4
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x1x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:253
2x1x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:196
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1;TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:3
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:255
2x1x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:239
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1;TransposedConvBinWinoRxS<2-3>:3;TransposedConvBinWinoRxS<3-2>:3
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1;TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:211
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64;TransposedConvBinWinoRxS<2-3>:12;TransposedConvBinWinoRxS<3-2>:16
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x1x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x1x1x1x1x1x1x1x64x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x1x1x1x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x1x1x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x1x1x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x1x1x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x1x1x1x4x4x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x1x1x1x1x4x4x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x1x1x1x1x4x4x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x1x1x1x1x4x4x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1x1x1x1x4x4x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x1x1x1x4x4x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x1x2003x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2107x80x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2129x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2129x80x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x213x80x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x213x80x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2154x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2154x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x222x80x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x222x80x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2278x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2278x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x228x80x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x228x80x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2363x80x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x243x80x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x243x80x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2463x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2463x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x248x80x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x248x80x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2494x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2494x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2537x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2537x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x264x80x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x264x80x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2688x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2688x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2725x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2725x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2758x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2758x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x275x80x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x275x80x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x286x80x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x286x80x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2887x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2887x80x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2890x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2890x80x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x2928x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2928x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2993x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2993x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x1x2x2x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x1x2x2x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x2x2x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x307x80x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x307x80x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x312x80x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x312x80x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x318x80x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x318x80x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x327x80x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x327x80x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x338x80x1x3x3x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x344x80x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x344x80x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x344x80x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x344x80x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x358x80x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x358x80x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x370x80x1x3x3x1x256x150x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x370x80x1x3x3x1x256x150x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x388x80x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x388x80x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x390x80x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x390x80x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x396x80x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x396x80x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+8
2x1x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[9];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+8
2x1x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x1x3x3x1x3x3x1x2x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x3x3x1x3x3x1x2x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x3x3x1x4x4x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x1x3x3x1x4x4x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1x3x3x1x4x4x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x1x3x3x1x4x4x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x1x3x3x1x4x4x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x1x3x3x1x4x4x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x1x400x80x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x400x80x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x412x80x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x412x80x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x423x80x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x423x80x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x432x80x1x3x3x1x256x119x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x432x80x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x432x80x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x450x80x1x3x3x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x450x80x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x450x80x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x461x80x1x3x3x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x466x80x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x466x80x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x466x80x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x484x80x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x488x80x1x3x3x1x256x105x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x488x80x1x3x3x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x48x480x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x48x480x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x1x494x80x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x494x80x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x496x80x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x504x80x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x504x80x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x508x80x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x508x80x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x517x80x1x3x3x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x527x80x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x527x80x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x528x80x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x528x80x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x536x80x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x536x80x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x539x80x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x539x80x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x541x80x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x541x80x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x543x80x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x543x80x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x548x80x1x3x3x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x549x80x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x555x80x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x555x80x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x560x80x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x561x80x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x562x80x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x570x80x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x570x80x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x573x80x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x576x80x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x576x80x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x580x80x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x581x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x581x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x582x80x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x587x80x1x3x3x1x256x67x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x591x80x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x596x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x596x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x598x80x1x3x3x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x598x80x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x598x80x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x5x5x1x3x3x1x2x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x2x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x2x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x2x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x5x5x1x3x3x1x2x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x5x5x1x3x3x1x2x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x5x5x1x3x3x1x2x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x610x80x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x612x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x612x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x613x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x613x80x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x613x80x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x613x80x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x616x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x616x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x616x80x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x618x80x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x620x80x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x620x80x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x623x80x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x626x80x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x626x80x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x628x80x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x628x80x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x629x80x1x3x3x1x256x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x633x80x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x641x80x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x643x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x643x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x645x80x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x646x80x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x647x80x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x647x80x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x651x80x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x652x80x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x652x80x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x656x80x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x656x80x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x656x80x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x656x80x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x662x80x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x662x80x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x663x80x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x663x80x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x668x80x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x668x80x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x671x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x671x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x673x80x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x673x80x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x673x80x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x674x80x1x3x3x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x685x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x685x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x689x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x689x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x690x80x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x690x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x690x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x700x80x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x700x80x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x700x80x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x702x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x702x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x706x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x706x80x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x714x80x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x714x80x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x716x80x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x716x80x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x717x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x717x80x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x725x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x725x80x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x734x80x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x734x80x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x734x80x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x750x80x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x750x80x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x754x80x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x754x80x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x756x80x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x756x80x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x758x80x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x758x80x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x762x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x762x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x765x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x765x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x777x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x777x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x778x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x778x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x780x80x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x780x80x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x785x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x785x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x791x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x791x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x7x7x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x7x7x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x7x7x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+8
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x1x7x7x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x1x7x7x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x1x7x7x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x801x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x801x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x802x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x802x80x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x803x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x803x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x807x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x807x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x80x120x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x1x80x120x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1x80x120x1x1x1x1x32x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x1x80x120x1x1x1x1x32x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x1x80x120x1x1x1x1x32x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x1x80x120x1x1x1x1x32x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x1x810x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x810x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x812x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x812x80x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x817x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x817x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x818x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x818x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x822x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x822x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x823x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x823x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x825x80x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x825x80x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x836x80x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x836x80x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x838x80x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x838x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x838x80x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x843x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x843x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x846x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x846x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x848x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x848x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x857x80x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x863x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x863x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x877x80x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x877x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x877x80x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x884x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x884x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x885x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x885x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x890x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x890x80x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x893x80x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x893x80x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x895x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x895x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x901x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x901x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x906x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x906x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x908x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x908x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x912x80x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x925x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x925x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x935x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x935x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x941x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x941x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x943x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x943x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x953x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x953x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x958x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x958x80x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x959x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x959x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x962x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x962x80x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x968x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x968x80x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x969x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x969x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x987x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x987x80x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x994x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x1x994x80x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x997x80x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x997x80x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x1x9x9x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x9x9x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,31[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x9x9x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x9x9x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x1x9x9x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x1x9x9x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x1x9x9x1x3x3x1x2x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x200x128x128x1x1x1x1x1200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x200x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x200x128x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x200x128x128x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x200x128x128x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x200x128x128x1x3x3x1x200x1x1x1x0x1x1x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x128x128x1x3x3x1x200x1x1x1x0x2x2x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x14x14x1x1x1x1x1200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x200x14x14x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x200x14x14x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x200x14x14x1x3x3x1x200x1x1x1x0x1x1x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x28x28x1x5x5x1x200x1x2x2x0x2x2x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x32x32x1x5x1x1x200x1x2x0x0x1x1x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x56x56x1x1x1x1x276x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x200x56x56x1x3x3x1x200x4x1x1x0x1x1x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x200x64x64x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x200x64x64x1x1x5x1x200x1x0x2x0x1x1x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x64x64x1x1x5x1x200x4x0x2x0x1x1x0x1x1x0x0x200xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x200x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x11x11x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x128x128x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2016x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x14x14x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x14x14x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,6,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[6];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[3];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x21x21x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x21x21x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x30x46x1x1x1x1x1024x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x1024x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x1536x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x1536x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x1536x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x1536x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x30x46x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x30x46x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2016x30x46x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2016x30x46x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2016x30x46x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2016x30x46x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2016x30x46x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2016x30x46x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2016x30x46x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x30x46x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2016x30x46x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x2016x30x46x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2016x30x46x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x30x46x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xB=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2016x30x46x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2016x32x32x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,65[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2016x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2016x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2016x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2016x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2016x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2016x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2016x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x2016x59x91x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2016x59x91x1x3x3x1x2016x10x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x12x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x59x91x1x3x3x1x2016x14x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x16x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2016x59x91x1x3x3x1x2016x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2016x59x91x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x2x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x6x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x7x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x59x91x1x3x3x1x2016x8x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2016x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2016x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2016x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2016x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2016x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2016x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2016x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2016x7x7x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x201x14x14x1x5x5x1x201x1x2x2x0x1x1x0x1x1x0x0x201xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2020x1024x1024x1x3x3x1x2020x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x2020x112x112x1x3x3x1x2020x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2020x1x1x1x1x1x1x505x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2020x512x512x1x1x1x1x2020x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2042x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x100x136x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x100x136x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x100x152x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x100x152x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x2048x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x2048x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x2048x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x112x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x112x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2048x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x128x128x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x2048x128x128x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2048x128x128x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x128x128x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x128x128x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x128x128x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,4,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[4];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x12x12x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x12x12x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x12x12x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+8
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x12x12x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+8
2x2048x12x12x1x7x7x1x2048x4x3x3x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x13x13x1x1x1x1x512x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x1x1x1x512x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x13x13x1x1x1x1x512x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x1x1x1x512x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x1x1x1x512x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x1x1x1x512x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x1x1x1x512x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x1x1x1x512x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x1x1x1x512x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x1x1x1x512x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x1x1x1x512x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x13x13x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x13x13x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x13x13x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x13x13x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x13x13x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x2048x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x2048x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x14x14x1x1x1x1x512x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x14x14x1x1x1x1x512x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x512x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x512x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x14x14x1x1x1x1x512x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x1x1x1x512x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x8192x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x2048x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x14x14x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x14x14x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x15x15x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x15x15x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x15x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x15x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x15x15x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x15x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x15x15x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x15x15x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x15x15x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x15x15x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x15x15x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x16x32x1x3x1x1x2048x10x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x10x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x11x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x11x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x12x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x12x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x13x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x13x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x14x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x14x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x15x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x15x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x16x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x16x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x17x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x17x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x18x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x18x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x19x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x19x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x1x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x16x32x1x3x1x1x2048x1x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x20x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x20x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x21x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x21x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x22x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x22x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x23x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x23x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x24x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x24x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x25x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x25x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x26x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x26x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x27x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x27x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x28x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x28x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x29x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x29x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x2x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x2x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x30x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x30x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x31x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x31x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x32x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x32x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x33x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x33x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x34x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x34x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x35x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x35x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x36x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x36x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x37x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x37x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x3x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x3x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x4x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x4x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x16x32x1x3x1x1x2048x5x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x5x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x6x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x6x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x7x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x7x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x8x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x8x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x16x32x1x3x1x1x2048x9x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x16x32x1x3x1x1x2048x9x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x18x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x18x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x18x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x18x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x18x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x18x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x18x42x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x19x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x19x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x19x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x19x37x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x19x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x19x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x1001x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2048x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x256x1x1x2x1x2048x10x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x10x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x11x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x11x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x12x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x12x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x13x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x13x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x14x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x14x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x15x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x15x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x16x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x16x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x17x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x17x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x18x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x18x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x19x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x19x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x1x256x1x1x2x1x2048x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x20x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x20x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x21x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x21x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x22x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x22x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x23x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x23x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x24x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x24x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x25x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x25x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x26x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x26x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x27x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x27x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x28x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x28x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x29x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x29x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x2x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x1x256x1x1x2x1x2048x2x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x30x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x30x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x31x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x31x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x32x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x32x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x33x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x33x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x34x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x34x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x35x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x35x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x1x256x1x1x2x1x2048x36x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x36x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x1x256x1x1x2x1x2048x37x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x37x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x1x256x1x1x2x1x2048x3x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x1x256x1x1x2x1x2048x3x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x4x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x1x256x1x1x2x1x2048x4x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x5x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x1x256x1x1x2x1x2048x5x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x6x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x6x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x1x256x1x1x2x1x2048x7x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x7x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x8x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x8x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x256x1x1x2x1x2048x9x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x1x256x1x1x2x1x2048x9x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x2048x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,272[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,272[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x2048x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x2048x1x512x1x1x2x1x2048x10x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x11x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x12x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x13x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x14x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x15x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x16x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x17x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x18x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x19x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x20x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x21x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x22x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x23x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x24x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x25x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x26x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x27x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x28x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x29x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x2x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x30x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x31x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x32x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x1x512x1x1x2x1x2048x33x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x34x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x35x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x36x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x37x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x3x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x4x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x5x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x6x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x1x512x1x1x2x1x2048x7x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x8x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x1x512x1x1x2x1x2048x9x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x20x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x20x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x20x20x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x20x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x20x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x20x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x20x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x20x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x20x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x20x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x20x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x27x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x20x27x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x27x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,5,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x20x30x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x20x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x20x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x31x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x20x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x31x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x32x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x20x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x20x36x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x20x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x20x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x36x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x20x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x20x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x38x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x20x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x20x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x20x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x20x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x20x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x20x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x20x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x20x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x20x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x20x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x20x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x20x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x20x42x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x21x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x21x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x26x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x26x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x21x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x26x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x26x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x21x26x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x26x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x21x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x26x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x21x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x21x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x21x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x21x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x32x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x33x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x35x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x21x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x21x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x37x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x21x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x21x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x21x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x21x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x21x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x21x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x21x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x21x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x21x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x21x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x21x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x21x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x21x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x21x42x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x21x43x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x22x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x22x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x22x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x22x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x22x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x22x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[4];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x22x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x22x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x22x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x22x30x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x22x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x30x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x22x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[6];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x22x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x22x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x22x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x22x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x22x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x32x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x33x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x33x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x33x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x33x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x22x33x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x33x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x22x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x33x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x34x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x22x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x22x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x22x36x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x22x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x22x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x22x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x22x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x22x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x22x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x38x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x22x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x22x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x22x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x22x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x22x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x22x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x22x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[6];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x22x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x22x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x22x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x22x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x22x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x22x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x22x42x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x23x23x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x23x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x23x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x23x23x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x23x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x23x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x23x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x31x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x31x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x31x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x23x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x23x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x23x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x23x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x33x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x35x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x35x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x23x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,18[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x35x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x23x35x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x35x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x23x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x23x35x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x35x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x23x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x37x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x23x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x23x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x37x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x37x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x23x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x23x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x23x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x23x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x23x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x23x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x23x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x23x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x23x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x41x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x23x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x23x41x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x23x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x23x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x23x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x23x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x23x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x23x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x23x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x23x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x23x42x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x23x43x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x24x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x24x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x24x24x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2048x24x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x26x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x24x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x31x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x24x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x32x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x32x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x24x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x24x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x34x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x24x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x24x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x36x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x36x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x2048x24x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x36x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x36x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x24x37x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x24x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x37x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x24x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x24x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x37x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x24x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x24x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x38x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x39x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x39x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x24x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x24x39x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x39x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x24x39x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x39x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x24x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x39x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x40x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x40x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x24x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x24x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x24x40x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x40x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x24x40x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x40x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x40x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x24x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x24x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x24x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x24x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x24x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x24x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x24x42x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x24x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x24x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x24x42x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x24x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x24x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x24x42x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x24x42x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x2048x256x256x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x256x256x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x25x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x25x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x25x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x25x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x27x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x25x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x33x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x33x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x33x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x34x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x34x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x25x34x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x34x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x25x34x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x34x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x34x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x34x1x3x3x1x256x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x34x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x35x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x35x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x36x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x25x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x25x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x37x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x37x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x37x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x38x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x38x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x25x38x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x38x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x25x38x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x38x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x25x38x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x25x38x1x3x3x1x256x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x38x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x39x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x25x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x25x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x25x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x25x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x25x40x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x25x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x25x41x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x25x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x41x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x25x41x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x25x41x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x25x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x25x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x25x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x25x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x25x42x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x25x43x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x26x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x26x20x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x26x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x26x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x26x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x26x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x26x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x26x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x26x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x26x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x26x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x26x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x26x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x26x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x26x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x26x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x32x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x34x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x38x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x38x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x26x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[6];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x26x42x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x27x20x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x27x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x27x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x27x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x27x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x27x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x27x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x27x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x27x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x27x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x27x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x27x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x27x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x27x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x27x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x27x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x27x25x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x27x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x33x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x35x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x39x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x27x39x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x27x41x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x27x43x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x28x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,6,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[6];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x28x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x28x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x28x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x28x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x28x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x28x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x28x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x28x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x28x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x28x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x28x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x28x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x25x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x25x1x3x3x1x256x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x25x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x26x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x2048x28x28x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7]
2x2048x28x28x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Filter1x1Stride1Pad0, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x2048x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x28x28x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x2048x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,65[1];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x2048x28x28x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x2048x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x28x28x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+16
2x2048x28x28x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+16
2x2048x28x28x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x28x28x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x28x28x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x28x28x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x28x28x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x28x28x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x28x28x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x2048x28x28x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x2048x28x28x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x28x28x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x28x28x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x28x28x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x2048x28x28x1x3x3x1x256x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x1x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x1x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x1x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x1x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x28x28x1x3x3x1x256x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[6];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x28x28x1x3x3x1x256x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x28x28x1x3x3x1x256x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x28x28x1x3x3x1x256x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x29x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x29x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x29x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x29x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x29x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x29x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x29x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x29x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x29x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x29x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x29x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x29x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x29x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x29x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x29x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x29x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x29x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x29x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x29x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x29x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x29x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x29x29x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+16
2x2048x29x29x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+32
2x2048x29x29x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x29x29x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x29x29x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x29x29x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x29x29x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x29x29x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x29x29x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x29x29x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x29x29x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x29x29x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x29x29x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x2048x29x29x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x29x29x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x29x29x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x29x29x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x30x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x30x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x30x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x30x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x30x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x30x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x30x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x30x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x30x22x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x30x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x30x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x30x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x30x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x30x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x22x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x30x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x30x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x30x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x30x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x30x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x30x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x30x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x30x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,6,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[6];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x30x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x30x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x30x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x30x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x30x30x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x30x30x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x2048x30x30x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x30x30x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x30x30x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x30x46x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x31x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x31x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x31x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x31x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x20x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x31x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x20x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x31x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x31x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x31x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x31x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x31x23x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x31x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x31x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x23x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x31x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x31x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x31x24x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x31x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x31x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x31x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x31x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x31x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x31x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x31x24x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x31x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x31x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x31x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x31x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x31x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x31x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x31x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x32x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x32x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x32x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x32x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x32x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x32x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x32x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x32x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x32x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x32x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x32x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x32x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x32x23x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x32x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x32x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x23x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x32x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x32x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x32x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x32x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x32x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x32x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x32x32x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x32x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x32x32x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x32x32x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x2048x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x2048x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x2048x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x32x32x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x32x32x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2048x32x32x1x9x9x1x2048x1x4x4x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x33x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x33x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x33x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x33x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x33x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x33x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x33x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x33x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x33x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x33x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x33x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x33x22x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x33x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x33x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x33x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x33x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x33x22x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x33x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x33x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x33x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x33x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x33x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x33x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x33x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x33x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x33x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x33x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x2048x33x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x33x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x33x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x33x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x33x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x33x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x33x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x33x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x33x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x34x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x34x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x34x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x34x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x34x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,6,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x34x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x34x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x34x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x34x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x34x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x34x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x34x22x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x34x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x34x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x22x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x34x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x34x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x34x22x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,6,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x34x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x34x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x34x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x34x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x34x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x34x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x34x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x34x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x34x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x34x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x34x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x34x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x34x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x34x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x34x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x34x25x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x34x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x34x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x34x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x34x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x34x25x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x35x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x35x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x35x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x35x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x35x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x35x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x35x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x35x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x35x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x35x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x35x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x35x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x35x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x35x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x35x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x35x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x35x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x35x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x35x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x35x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x35x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x35x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x35x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x35x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x35x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x35x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x35x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x35x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x35x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x36x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x36x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+8
2x2048x36x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x36x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,6,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x36x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x36x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x36x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x36x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x36x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x36x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x36x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x36x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x36x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x36x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x36x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x23x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x36x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x36x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x23x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x36x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x23x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x36x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x36x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x36x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x36x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x36x24x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x36x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x36x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x36x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x36x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x36x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x36x24x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x36x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x36x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x36x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x36x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x36x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x36x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x37x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x37x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x37x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x37x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x37x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x37x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x37x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x37x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x37x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x37x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x37x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x37x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x37x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x37x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x37x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x37x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x37x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x37x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x37x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x37x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x37x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x37x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x37x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x37x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x37x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x37x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x38x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x38x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x38x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x38x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x38x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x38x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x38x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x38x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x38x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x38x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x38x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x38x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x38x24x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x38x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x38x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x38x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x38x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x38x24x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x38x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x38x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x38x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x38x25x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x38x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x38x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x38x25x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x38x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x38x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x38x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x38x25x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x38x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x39x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x39x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x39x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x39x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x39x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x39x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x39x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x39x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x39x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x39x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x39x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x39x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x39x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x39x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x39x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x39x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x39x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x3x3x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x2048x3x3x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x40x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x40x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x40x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x40x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x40x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x40x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x40x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x40x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x40x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x40x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x40x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x40x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x40x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x40x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x40x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x40x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x40x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x40x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x40x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x40x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x40x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x40x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x40x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x40x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x40x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x40x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x40x24x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x40x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x40x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x40x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x40x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x40x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x40x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x40x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x41x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x41x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x41x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x41x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x41x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x41x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x41x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x41x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x41x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x41x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x41x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x41x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x41x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x41x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x41x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x41x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x41x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x41x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x41x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x41x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x41x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x41x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x41x25x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x41x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x42x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x42x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x42x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x42x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x42x20x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x42x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x42x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x42x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x42x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x42x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x42x21x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x42x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x42x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x21x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x42x21x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x42x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x42x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x42x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x42x22x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x42x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x42x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x42x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x42x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x23x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x42x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x42x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x42x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x42x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x42x24x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x42x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x42x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x42x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x42x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x42x25x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x42x26x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x43x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x43x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x43x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x2048x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x2048x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x2048x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x2048x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x48x32x1x3x1x1x2048x10x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x11x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x12x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x13x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x14x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x15x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x16x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x17x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x18x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x19x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x1x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x48x32x1x3x1x1x2048x20x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x21x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x22x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x23x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x24x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x25x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x26x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x27x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x28x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x29x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x2x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x48x32x1x3x1x1x2048x30x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x48x32x1x3x1x1x2048x31x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x48x32x1x3x1x1x2048x32x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2048x48x32x1x3x1x1x2048x33x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x34x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x35x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x36x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x37x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x3x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x4x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x5x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x6x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x7x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x8x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x1x1x2048x9x1x0x0x3x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x48x32x1x3x3x1x768x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x48x32x1x3x3x1x768x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,8,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x2048x48x32x1x3x3x1x768x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x48x32x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x48x32x1x3x3x1x768x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x48x32x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x48x32x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x3x3x1x768x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x48x32x1x3x3x1x768x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x48x32x1x3x3x1x768x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+8
2x2048x48x32x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x48x32x1x3x3x1x768x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x3x3x1x768x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,237[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x3x3x1x768x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,237[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x48x32x1x3x3x1x768x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x2048x48x32x1x3x3x1x768x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x48x32x1x3x3x1x768x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x2048x48x32x1x3x3x1x768x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x49x49x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x4x4x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x55x55x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x55x55x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x55x55x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x55x55x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+16
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+8
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x2048x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+8
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x2048x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x2048x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2
2x2048x56x56x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x56x56x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6
2x2048x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12
2x2048x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16
2x2048x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x57x57x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x57x57x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x57x57x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x5x5x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x5x5x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x2048x5x5x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x5x5x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x2048x62x62x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x64x64x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x64x64x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x64x64x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x64x64x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x64x64x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2048x64x64x1x5x5x1x2048x4x2x2x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x64x64x1x9x9x1x2048x1x4x4x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x65x65x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x6x6x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[5];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x6x6x1x3x3x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x6x6x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,4,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[4];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x6x6x1x3x3x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:165
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:160
2x2048x7x7x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,280[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:201
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:160
2x2048x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:252
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:252
2x2048x7x7x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x2048x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:220
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:192
2x2048x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:247
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:214
2x2048x7x7x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];TransposedConvBinWinoRxS<3-2>:254
2x2048x7x7x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:255
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:240
2x2048x7x7x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:242
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:231
2x2048x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x2048x7x7x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:212
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:194
2x2048x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,6,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[6];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x2048x7x7x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[4];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x2048x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,117;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x3072x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,125;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x3072x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,117;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,117;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x4100x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,53[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:243
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:201
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:192
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[3];TransposedConvBinWinoRxS<3-2>:80
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];TransposedConvBinWinoRxS<3-2>:99
2x2048x7x7x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:97
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:88
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:240
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:236
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:232
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:231
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,48;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:235
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:235
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:158
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:147
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,280[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];TransposedConvBinWinoRxS<3-2>:229
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];TransposedConvBinWinoRxS<3-2>:184
2x2048x7x7x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];TransposedConvBinWinoRxS<3-2>:234
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:230
2x2048x7x7x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:233
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];TransposedConvBinWinoRxS<3-2>:246
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];TransposedConvBinWinoRxS<3-2>:255
2x2048x7x7x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:236
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:145
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:144
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:62
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:48
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x2048x7x7x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x1x1x1x512x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x8192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x7x7x1x1x1x1x976x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x1x1x1x976x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+8
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x7x7x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x2048x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x2048x7x7x1x5x5x1x2048x4x2x2x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x7x7x1x7x7x1x2048x1x3x3x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x7x7x1x9x9x1x2048x4x4x4x0x1x1x0x1x1x0x0x2048xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2048x8x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x8x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x32x1x1x1x1x4096x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x4096x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x4096x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x32x1x1x1x1x4096x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x32x1x1x1x1x4096x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x4096x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x32x1x1x1x1x4096x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x32x1x1x1x1x4096x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x2048x8x8x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,95;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x2048x8x8x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x320x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x384x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x384x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x448x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2048x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x448x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x2048x8x8x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x2048x8x8x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2048x8x8x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x2048x8x8x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2048x8x8x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2048x8x8x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2048x8x8x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+16
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+4
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x2048x8x8x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2048x8x8x1x3x3x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2048x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x128x128x1x1x1x1x344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x128x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x128x128x1x3x3x1x2064x4x1x1x0x1x1x0x1x1x0x0x2064xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2064x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2064x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2064x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2064x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2064x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2064x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2064x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x14x14x1x3x3x1x2064x1x1x1x0x1x1x0x1x1x0x0x2064xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2064x17x17x1x1x1x1x344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x17x17x1x1x1x1x344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x17x17x1x3x3x1x2064x1x1x1x0x1x1x0x1x1x0x0x2064xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2064x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x32x32x1x1x1x1x368x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x64x64x1x1x1x1x368x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x64x64x1x3x3x1x2064x4x1x1x0x1x1x0x1x1x0x0x2064xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2064x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2064x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2064x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2064x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2064x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2064x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2064x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2064x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2064x7x7x1x5x5x1x2064x1x2x2x0x1x1x0x1x1x0x0x2064xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2080x5x5x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2080x62x62x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2082x32x32x1x3x3x1x2082x1x1x1x0x1x1x0x1x1x0x0x2082xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2082x64x64x1x3x3x1x2082x1x1x1x0x1x1x0x1x1x0x0x2082xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x208x128x128x1x1x1x1x440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x208x128x128x1x3x3x1x208x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x208x128x128x1x3x3x1x208x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x208x14x14x1x1x1x1x440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x208x14x14x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x26xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x208x14x14x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x208x14x14x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x208x14x14x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x14x14x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x208x14x14x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x14x14x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x208x14x14x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x208x14x14x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x208x14x14x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x208x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x208x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x208x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x208x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x208x14x14x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x208x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x208x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x208x14x14x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x208x14x14x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x208x14x14x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x208x14x14x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x208x14x14x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x208x14x14x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x208x1x1x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x208x1x1x1x1x1x1x52x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x208x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x208x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x28x28x1x3x3x1x208x4x1x1x0x2x2x0x1x1x0x0x26xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x208x32x32x1x1x1x1x1148x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x208x32x32x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x208x32x32x1x1x1x1x624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x208x32x32x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x208x3x3x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x208x64x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x64x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x208x64x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x208x64x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x208x64x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x208x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x208x64x64x1x1x1x1x1148x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x208x64x64x1x1x1x1x440x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x208x64x64x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x208xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x208x64x64x1x3x3x1x208x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x208x64x64x1x3x3x1x208x4x1x1x0x1x1x0x1x1x0x0x208xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x208x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x208x7x7x1x1x1x1x1040x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x7x7x1x1x1x1x1148x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x7x7x1x1x1x1x1160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x7x7x1x1x1x1x1228x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x7x7x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x208x9x9x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x20x1024x1024x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x1024x1024x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x112x112x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x112x112x1x3x3x1x20x4x1x1x0x2x2x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x20x128x128x1x1x1x1x30x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x128x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x128x128x1x3x3x1x20x1x1x1x0x1x1x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x20x128x128x1x3x3x1x20x1x1x1x0x2x2x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x20x1x1x1x1x1x1x164x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x1x1x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x256x256x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x256x256x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x256x256x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x256x256x1x1x1x1x7x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x28x28x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x28x28x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x28x28x1x1x1x1x30x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x28x28x1x7x7x1x20x4x3x3x0x1x1x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x20x512x512x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x20x512x512x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x56x56x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x56x56x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x20x56x56x1x3x3x1x20x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x20x64x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x210x256x256x1x3x3x1x210x1x1x1x0x1x1x0x1x1x0x0x210xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x210x512x512x1x1x1x1x50x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x210x56x56x1x3x3x1x210x1x1x1x0x1x1x0x1x1x0x0x210xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x210x64x64x1x1x1x1x1260x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x210x64x64x1x1x1x1x1260x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x128x128x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x128x128x1x1x1x1x386x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x128x128x1x1x1x1x386x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x2112x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2112x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2112x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2112x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2112x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x14x14x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2112x14x14x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2112x14x14x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x14x14x1x3x3x1x2112x4x1x1x0x1x1x0x1x1x0x0x2112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2112x1x1x1x1x1x1x132x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x1x1x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x1x1x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x64x64x1x3x3x1x2112x1x1x1x0x1x1x0x1x1x0x0x2112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2112x64x64x1x3x3x1x2112x1x1x1x0x2x2x0x1x1x0x0x264xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2112x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x2112x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2112x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2112x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2112x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2112x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2112x7x7x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2112x7x7x1x3x3x1x2112x1x1x1x0x1x1x0x1x1x0x0x2112xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x211x7x7x1x1x1x1x1266x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x213x128x128x1x1x1x1x67x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x213x14x14x1x1x1x1x67x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x213x64x64x1x5x5x1x213x1x2x2x0x1x1x0x1x1x0x0x213xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2144x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x215x128x128x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x215x129x129x1x3x3x1x215x1x0x0x0x2x2x0x1x1x0x0x215xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x215x14x14x1x1x1x1x93x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x215x257x257x1x3x3x1x215x1x0x0x0x2x2x0x1x1x0x0x215xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x215x64x64x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2160x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2160x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2160x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2160x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2160x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2160x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2160x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2160x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2160x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2160x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2160x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2160x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2160x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x216x128x128x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x216x128x128x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x216x128x128x1x5x5x1x216x1x2x2x0x1x1x0x1x1x0x0x216xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x216x128x128x1x7x7x1x216x1x3x3x0x1x1x0x1x1x0x0x216xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x216x14x14x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x216x14x14x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x216x14x14x1x2x2x1x216x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x216x14x14x1x3x3x1x216x1x1x1x0x1x1x0x1x1x0x0x216xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x216x1x1x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x216x1x1x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x216x1x1x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x216x256x256x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x216x256x256x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x216x256x256x1x1x1x1x576x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x216x28x28x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x216x28x28x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+128
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+128
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x216x28x28x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 32, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 2, 2, 2, 1, 1, 2>+128
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+64
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+128
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+-1
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x216x28x28x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x216x28x28x1x1x1x1x576x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x216x28x28x1x7x7x1x216x4x3x3x0x1x1x0x1x1x0x0x216xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x216x512x512x1x3x3x1x216x1x1x1x0x2x2x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2176x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x2176x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x217x128x128x1x1x1x1x1302x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x217x14x14x1x1x1x1x1302x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x217x14x14x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x217x14x14x1x5x5x1x217x4x2x2x0x1x1x0x1x1x0x0x217xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x217x1x1x1x1x1x1x34x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x217x64x64x1x5x5x1x217x1x2x2x0x1x1x0x1x1x0x0x217xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x219x64x64x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x21x1024x1024x1x1x1x1x126x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x21x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x21x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x21x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x21x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x21x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x21x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x21x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x21x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x21x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x21x512x512x1x1x1x1x126x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x21x6x7x1x3x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x21x6x7x1x3x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2208x256x256x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x220x7x7x1x1x1x1x220x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x220x7x7x1x1x1x1x880x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x220x7x7x1x3x3x1x220x1x1x1x0x1x1x0x1x1x0x0x220xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2240x128x128x1x1x1x1x800x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2240x14x14x1x3x3x1x2240x4x1x1x0x2x2x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2240x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2240x32x32x1x1x1x1x2240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2240x7x7x1x1x1x1x2240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1024x1024x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x112x112x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x126x126x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x126x126x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x128x128x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x128x128x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x128x128x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x128x128x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x128x128x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x128x128x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x128x128x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x12x12x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x139x139x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x139x139x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x139x139x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x139x139x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x139x139x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x139x139x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x139x139x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x139x139x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x13x25x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x13x25x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x13x25x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x13x25x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x13x25x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x13x25x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x13x25x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x13x25x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x140x140x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x140x140x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x140x140x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x140x140x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x140x140x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x140x140x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x140x140x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x140x140x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x140x140x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x140x140x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x141x141x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x141x141x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x14x14x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x14x14x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x224x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x224x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x224x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x14x14x1x3x3x1x112x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x224x14x14x1x3x3x1x112x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x14x14x1x3x3x1x112x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x14x14x1x3x3x1x112x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x14x14x1x3x3x1x112x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x224x14x14x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x224x14x14x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,5,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x224x14x14x1x3x3x1x112x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x224x14x14x1x3x3x1x112x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x14x14x1x3x3x1x112x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x14x14x1x3x3x1x112x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x224x14x14x1x3x3x1x112x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x14x14x1x3x3x1x112x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x224x14x14x1x3x3x1x112x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x14x14x1x3x3x1x112x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x224x14x14x1x3x3x1x112x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x14x14x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x14x14x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x14x14x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x15x21x1x3x3x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x224x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x15x21x1x3x3x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x15x21x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x15x21x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x15x21x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x224x15x21x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x224x15x21x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x15x21x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x1x7x1x192x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x224x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x224x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x17x17x1x1x7x1x192x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x224x17x17x1x1x7x1x192x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x1x7x1x192x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+2
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+2
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x1x7x1x192x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x192x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x192x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x1x7x1x192x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x1x7x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x224x17x17x1x1x7x1x224x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x1x7x1x224x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x1x7x1x224x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x1x7x1x224x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x224x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x1x7x1x224x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x3x3x1x224x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x224x17x17x1x3x3x1x224x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x17x17x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x3x3x1x256x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x7x1x1x192x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x224x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x7x1x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x224x17x17x1x7x1x1x192x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x7x1x1x192x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x17x17x1x7x1x1x192x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x224x17x17x1x7x1x1x192x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x224x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x224x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x224x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x224x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x256x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x7x1x1x256x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x7x1x1x256x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x256x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x17x17x1x7x1x1x256x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x17x17x1x7x1x1x256x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x14x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[8];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[10];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x224x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[9];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x1x1x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x8x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+32
2x224x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x1x1x1x1x1x1x8x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x1x1x1x1x1x1x8x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x224x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x21x15x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x21x15x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x21x15x1x3x3x1x256x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x21x15x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+64
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x235x362x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x362x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x362x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x362x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x362x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x362x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x362x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x362x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x224x235x362x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x224x235x362x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x362x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x224x235x362x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x362x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x224x235x362x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x362x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x224x235x362x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x362x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x362x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x362x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x10x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x12x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x14x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x224x235x362x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x362x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x362x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x362x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x224x235x363x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x224x235x363x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x224x235x363x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x224x235x363x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,97[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x363x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x363x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x363x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,97[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x363x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x235x363x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x224x235x363x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x224x235x363x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x363x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x363x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x235x363x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x363x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x224x235x363x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x363x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x224x235x363x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x235x363x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x224x235x363x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x3x3x1x224x2x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x3x3x1x224x6x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x235x363x1x3x3x1x224x7x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x235x363x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x235x363x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x224x253x253x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x256x256x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x256x256x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x256x256x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x256x256x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x25x13x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x224x25x13x1x3x3x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x224x25x13x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x224x25x13x1x3x3x1x192x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x224x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x224x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x224x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x28x28x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x28x28x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x28x28x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x28x28x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x29x29x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x224x33x33x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x224x33x33x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x33x33x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x33x33x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x33x33x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x33x33x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x33x33x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x33x33x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x33x33x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x33x33x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x33x33x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x33x33x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x34x34x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x34x34x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x34x34x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x34x34x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x34x34x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x34x34x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x34x34x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x34x34x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x34x34x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x34x34x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x35x35x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x35x35x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x35x35x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x35x35x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x35x35x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x35x35x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x35x35x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x224x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x35x35x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x224x35x35x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x224x35x35x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x224x35x35x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x224x35x35x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x224x35x35x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x224x35x35x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x35x35x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x224x35x35x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x224x35x35x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x224x35x35x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x224x35x35x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x35x35x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x35x35x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x35x35x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x35x35x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x35x35x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x35x35x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x35x35x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x35x35x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x35x35x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x35x35x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x37x37x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x38x38x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x469x724x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,133[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x224x469x724x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,133[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x224x469x724x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x469x724x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x469x724x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x469x724x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x469x724x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x469x724x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x469x724x1x3x3x1x224x10x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x469x724x1x3x3x1x224x12x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x469x724x1x3x3x1x224x14x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x469x724x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x469x724x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x469x724x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x470x725x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x470x725x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x470x725x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x470x725x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x470x725x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x224x470x725x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x470x725x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x470x725x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,133[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x470x725x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x470x725x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x470x725x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x470x725x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x470x725x1x3x3x1x224x7x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x470x725x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x470x725x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x48x48x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x4x16384x1x1x1x1x449x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x224x4x196x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x4x196x1x1x1x1x449x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x224x4x4096x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x4x4096x1x1x1x1x449x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x224x512x512x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x512x512x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x512x512x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x512x512x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x224x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x224x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x224x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x224x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x224x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x56x56x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x56x56x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x62x62x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x62x62x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x224x64x128x1x3x3x1x112x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x224x64x64x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x224x64x64x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x64x64x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x224x64x64x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x224x64x64x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x64x64x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x7x7x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,1,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,83[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x224x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x7x7x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x224x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x224x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x224x7x7x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x224x7x7x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x224x7x7x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x226x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x226x14x14x1x5x5x1x226x1x2x2x0x1x1x0x1x1x0x0x226xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x226x1x1x1x1x1x1x33x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x228x256x256x1x1x1x1x50x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x228x56x56x1x3x3x1x228x1x1x1x0x2x2x0x1x1x0x0x228xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x22x1x1x1x1x1x1x292x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x22x1x1x1x1x1x1x502x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2301x64x64x1x3x3x1x2301x4x1x1x0x1x1x0x1x1x0x0x2301xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2301x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x2304x10x10x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x128x128x1x3x3x1x2304x1x1x1x0x2x2x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x128x128x1x3x3x1x2304x4x1x1x0x2x2x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x14x14x1x1x1x1x800x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x16x16x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2304x16x16x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2304x18x18x1x3x3x1x2304x1x1x1x0x1x1x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x18x18x1x3x3x1x2304x4x1x1x0x1x1x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x19x19x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x19x19x1x3x3x1x2304x4x1x1x0x1x1x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2304x19x19x1x5x5x1x2304x4x2x2x0x1x1x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x1x1x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2304x28x28x1x1x1x1x1552x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x2304x28x28x1x1x1x1x1552x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2304x32x32x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2304x32x32x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x32x32x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2304x64x64x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2304x64x64x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2304x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x7x7x1x1x1x1x1552x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Default, 32, 32, 1, 2, 4, 2, 1, 1>+16
2x2304x7x7x1x1x1x1x1552x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2304x7x7x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2304x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2304x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2304x7x7x1x3x3x1x2304x4x1x1x0x1x1x0x1x1x0x0x2304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2304x8x8x1x3x3x1x1536x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2304x9x9x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x230x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x230x128x128x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x2316x128x128x1x3x3x1x2316x4x1x1x0x2x2x0x1x1x0x0x2316xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2316x14x14x1x3x3x1x2316x1x1x1x0x2x2x0x1x1x0x0x2316xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2316x14x14x1x3x3x1x2316x4x1x1x0x2x2x0x1x1x0x0x2316xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2316x7x7x1x1x1x1x419x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x232x10x10x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x10x10x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x232x13x13x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x13x13x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x232x14x14x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x232x14x14x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x14x14x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x232x14x14x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x14x14x1x3x3x1x232x1024x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x512x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x14x14x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x15x15x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x15x15x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x256x256x1x1x1x1x696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x232x28x28x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x28x28x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x232x28x28x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x232x29x29x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x29x29x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x232x29x29x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x232x32x32x1x1x1x1x1016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x512x512x1x3x3x1x232x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x232x512x512x1x3x3x1x232x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x232x55x55x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x55x55x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x56x56x1x1x1x1x696x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x56x56x1x1x1x1x696x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x56x56x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x56x56x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x57x57x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x57x57x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x64x64x1x1x1x1x1130x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x64x64x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x232x64x64x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x64x64x1x1x1x1x1856x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x232x64x64x1x1x1x1x924x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x6x6x1x3x3x1x232x1024x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x6x6x1x3x3x1x232x1024x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x232x6x6x1x3x3x1x232x512x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x6x6x1x3x3x1x232x512x0x0x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x232x7x7x1x1x1x1x1266x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x232x7x7x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x232x7x7x1x1x1x1x232x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[10];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x232x7x7x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x232x7x7x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x232x7x7x1x1x1x1x232x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x232x7x7x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x232x7x7x1x3x3x1x232x1024x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x1024x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x1024x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x232x7x7x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x16x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x232x7x7x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x232x7x7x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x16x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x32x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x232x7x7x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x232x7x7x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x32x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x232x7x7x1x3x3x1x232x512x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x512x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x512x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x232x7x7x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x232x7x7x1x3x3x1x232x64x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x7x7x1x3x3x1x232x64x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x232x8x8x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x8x8x1x3x3x1x232x1024x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x232x8x8x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x232x8x8x1x3x3x1x232x512x1x1x0x2x2x0x1x1x0x0x232xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x233x128x128x1x1x1x1x818x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x233x14x14x1x1x1x1x818x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x233x64x64x1x1x1x1x818x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x234x128x128x1x3x3x1x156x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x234x14x14x1x1x1x1x1404x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x235x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x235x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x236x128x128x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x236x14x14x1x1x1x1x93x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x238x128x128x1x3x3x1x97x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x240x114x114x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x117x117x1x5x5x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x128x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x128x128x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x128x128x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x128x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x128x128x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x128x128x1x1x1x1x52x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x128x128x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x128x128x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x128x128x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x128x128x1x1x5x1x240x1x0x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x128x128x1x3x3x1x240x1x1x1x0x2x2x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x128x128x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x128x128x1x3x3x1x240x4x1x1x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x128x128x1x5x5x1x240x4x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x128x128x1x9x9x1x240x4x4x4x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x132x132x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x133x133x1x7x7x1x240x4x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x135x135x1x5x5x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x135x135x1x9x9x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x240x135x135x1x9x9x1x240x4x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x14x14x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x528x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x14x14x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x14x14x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x240x14x14x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x240x14x14x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x240x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x14x14x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x240x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x14x14x1x1x5x1x240x1x0x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x240x14x14x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x240x14x14x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x5x5x1x240x16x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x240x14x14x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x240x14x14x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x5x5x1x240x32x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x240x14x14x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x240x14x14x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x14x14x1x5x5x1x240x64x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x240x14x14x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x240x14x14x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x240x14x14x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x240x15x15x1x3x3x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x1x1x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x1x1x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x1x1x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x1x1x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x21x21x1x9x9x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x240x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x256x256x1x1x1x1x560x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x256x256x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x256x256x1x1x1x1x720x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x256x256x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x256x256x1x5x5x1x240x1x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x256x256x1x5x5x1x240x4x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x240x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x28x28x1x1x1x1x560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x28x28x1x1x1x1x560x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x240x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x240x28x28x1x1x1x1x60x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x240x28x28x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x3x3x1x240x4x1x1x0x2x2x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x28x28x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x16x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x1x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x32x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x28x28x1x5x5x1x240x64x2x2x0x2x2x0x1x1x0x0x240xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x30x30x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x30x30x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x30x30x1x5x5x1x240x4x2x2x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x32x32x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x32x32x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x32x32x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x32x32x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x32x32x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x3x3x1x3x3x1x240x4x0x0x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x240x4x1024x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x4x4096x1x1x1x1x481x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x240x512x512x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x512x512x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x512x512x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x512x512x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x512x512x1x3x3x1x240x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x56x56x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x240x56x56x1x3x3x1x240x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x5x5x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x64x64x1x1x1x1x1664x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x64x64x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x64x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x64x64x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x240x64x64x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x64x64x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x64x64x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x64x64x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x10xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x64x64x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x64x64x1x5x1x1x240x1x2x0x0x1x1x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x64x64x1x7x7x1x240x1x3x3x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x66x66x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x67x67x1x5x5x1x240x1x0x0x0x2x2x0x1x1x0x0x240xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x240x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x1x1x1x1440x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x7x7x1x1x1x1x864x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x7x7x1x1x1x1x864x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x240x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x240x7x7x1x3x3x1x240x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x3x3x1x240x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x3x3x1x240x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x240x7x7x1x3x3x1x240x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x240x7x7x1x3x3x1x240x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x240x7x7x1x3x3x1x240x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x240x7x7x1x3x3x1x240x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x240x7x7x1x3x3x1x240x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x240x7x7x1x3x3x1x240x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x2432x128x128x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x128x128x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2432x32x32x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2432x64x64x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x64x64x1x1x1x1x2304x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x64x64x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x64x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2432x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2432x7x7x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2432x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x243x1x1x1x1x1x1x2922x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x244x128x128x1x3x3x1x159x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x244x14x14x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x244x14x14x1x3x3x1x154x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x159x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x244x16x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x244x14x14x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x244x14x14x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x14x14x1x3x3x1x244x64x1x1x0x1x1x0x1x1x0x0x244xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+32
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+32
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x244x14x14x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x244x28x28x1x1x1x1x244x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x244x28x28x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x28x28x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x244x28x28x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x244x28x28x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x244x28x28x1x3x3x1x244x64x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x245x128x128x1x1x1x1x85x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x245x128x128x1x1x1x1x85x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x245x128x128x1x3x3x1x119x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x245x129x129x1x3x3x1x245x1x0x0x0x2x2x0x1x1x0x0x245xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x245x14x14x1x3x3x1x119x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x245x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x245x257x257x1x3x3x1x245x1x0x0x0x2x2x0x1x1x0x0x245xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x245x257x257x1x3x3x1x245x4x0x0x0x2x2x0x1x1x0x0x245xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x245x64x64x1x1x1x1x85x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x246x1x1x1x1x1x1x984x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x246x512x512x1x3x3x1x246x1x1x1x0x1x1x0x1x1x0x0x246xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x246x56x56x1x3x3x1x246x4x1x1x0x1x1x0x1x1x0x0x246xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x248x128x128x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x248x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x248x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x248x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x248x7x7x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x2496x32x32x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2496x64x64x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2496x64x64x1x3x3x1x2496x4x1x1x0x1x1x0x1x1x0x0x2496xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x1024x1024x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1024x1024x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x1024x1024x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x1024x1024x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, OddC, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x24x1024x1024x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x1024x1024x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1024x1024x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x1025x1025x1x2x2x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x24x1025x1025x1x2x2x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1025x1025x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x1025x1025x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x24x1026x1026x1x3x3x1x24x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x1026x1026x1x3x3x1x24x4x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,1,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x112x112x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x112x112x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x112x112x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x112x112x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x1x1x1x8x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x24x112x112x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x24x112x112x1x1x1x1x8x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x112x112x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x112x112x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x112x112x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x112x112x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x112x112x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x112x112x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x112x112x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x112x112x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x112x112x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x24x113x113x1x2x2x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x113x113x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x113x113x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x113x113x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x113x113x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x113x113x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x113x113x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x113x113x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x113x113x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x24x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x113x113x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x114x114x1x3x3x1x24x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x128x128x1x1x1x1x68x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x128x128x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x128x128x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x128x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x128x128x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x129x129x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x24x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x24x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x24x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x24x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x24x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x24x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x24x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x24x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x24x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x24x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x24x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x24x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x24x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x24x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x24x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x24x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x14x14x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x14x14x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x14x14x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x14x14x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x24x14x14x1x5x5x1x64x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x14x14x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x150x150x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x150x150x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x16x16x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x16x16x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x190x190x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x190x190x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x192x192x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x24x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x1x1x1x1x1x1x254x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x261x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x24x1x1x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x1x1x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x1x1x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+2
2x24x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x24x1x1x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x20x20x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x223x223x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x223x223x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x223x223x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x223x223x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x224x224x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x224x224x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x224x224x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x224x224x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x224x224x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x225x225x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x225x225x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x225x225x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x225x225x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x225x225x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x228x228x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x256x256x1x1x1x1x142x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x24x256x256x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x256x256x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x256x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x24x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x256x256x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x256x256x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x256x256x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x1x1x1x56x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x256x256x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x26x26x1x3x3x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x27x27x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x27x27x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x27x27x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x142x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x24x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x28x28x1x1x1x1x36x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x88x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x24x28x28x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x28x28x1x3x3x1x24x10x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x10x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x10x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x10x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x24x28x28x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+64
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x20x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x20x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x20x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x20x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x24x28x28x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x28x28x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x28x28x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x28x28x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x28x28x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x28x28x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x28x28x1x3x3x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x28x28x1x3x3x1x58x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x24x29x29x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x29x29x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x29x29x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x29x29x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x24x40x40x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x448x448x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9]
2x24x448x448x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x24x448x448x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x448x448x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x448x448x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x24x448x448x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x448x448x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x448x448x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x448x448x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x24x448x448x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x448x448x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x448x448x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x24x449x449x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x24x449x449x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x24x449x449x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x449x449x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x24x449x449x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x24x449x449x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x24x449x449x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x512x512x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x1x1x1x56x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x2x2x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x512x512x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x512x512x1x5x5x1x24x1x2x2x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x512x512x1x7x7x1x24x4x3x3x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x513x513x1x2x2x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x24x55x55x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x55x55x1x1x1x1x54x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x55x55x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x55x55x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x122x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x122x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,112[9];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[7];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[8];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x56x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x56x56x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x88x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x24x56x56x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x56x56x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x56x56x1x2x2x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x56x56x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x56x56x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x56x56x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+128
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x24x56x56x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x56x56x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x56x56x1x7x7x1x24x1x3x3x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x57x57x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x57x57x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x24x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x24x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x24x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x24x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x24x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x24x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x24x64x64x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x24x64x64x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x24x65x65x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x24x80x80x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x250x128x128x1x1x1x1x1500x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x250x128x128x1x3x3x1x176x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x250x14x14x1x1x1x1x1500x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x250x14x14x1x3x3x1x176x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2514x1x1x1x1x1x1x209x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2514x32x32x1x3x3x1x2514x1x1x1x0x1x1x0x1x1x0x0x2514xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2514x64x64x1x1x1x1x453x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2514x64x64x1x3x3x1x2514x4x1x1x0x1x1x0x1x1x0x0x2514xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2514x7x7x1x1x1x1x453x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2514x7x7x1x1x1x1x453x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2514x7x7x1x3x3x1x2514x4x1x1x0x1x1x0x1x1x0x0x2514xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x251x128x128x1x3x3x1x175x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x251x14x14x1x3x3x1x175x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x2520x128x128x1x3x3x1x2520x4x1x1x0x2x2x0x1x1x0x0x15xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2520x32x32x1x1x1x1x2520x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x253x128x128x1x3x3x1x181x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x253x14x14x1x3x3x1x181x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x253x14x14x1x3x3x1x235x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x2544x32x32x1x1x1x1x424x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2544x32x32x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2544x64x64x1x1x1x1x424x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2544x64x64x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2544x64x64x1x5x5x1x2544x1x2x2x0x1x1x0x1x1x0x0x2544xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2544x64x64x1x5x5x1x2544x4x2x2x0x1x1x0x1x1x0x0x2544xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2544x7x7x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x254x128x128x1x3x3x1x141x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x254x128x128x1x3x3x1x254x1x1x1x0x1x1x0x1x1x0x0x254xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x254x14x14x1x3x3x1x141x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x254x14x14x1x3x3x1x254x4x1x1x0x1x1x0x1x1x0x0x254xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x254x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x254x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x254x64x64x1x3x3x1x254x1x1x1x0x1x1x0x1x1x0x0x254xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x255x128x128x1x3x3x1x156x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x255x128x128x1x3x3x1x216x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x255x14x14x1x3x3x1x156x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x255x14x14x1x3x3x1x232x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x255x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x2560x10x10x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x2560x12x12x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x16x16x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:120
2x2560x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2560x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x16x16x1x3x3x1x1280x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x1x1x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x20x20x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x24x24x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x24x24x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2560x24x24x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2560x2x2x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x32x32x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x4x4x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x4x4x1x1x1x1x1280x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2560x4x4x1x1x1x1x1280x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x4x4x1x1x1x1x1280x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x4x4x1x3x3x1x1280x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x4x4x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x4x4x1x3x3x1x1280x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x4x4x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x7x7x1x1x1x1x1600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2560x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x7x7x1x5x5x1x2560x1x2x2x0x1x1x0x1x1x0x0x2560xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2560x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2560x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2560x8x8x1x1x1x1x960x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2560x8x8x1x1x1x1x960x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2560x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2560x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:107
2x2560x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2;TransposedConvBinWinoRxS<2-3>:252;TransposedConvBinWinoRxS<3-2>:245
2x2560x8x8x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:66
2x2560x8x8x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2560x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x2560x8x8x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1001x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1001x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1008x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1008x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1008x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1008x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x100x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x100x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x100x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x108x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x108x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x100x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x112x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x100x116x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x100x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x116x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x100x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x120x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x120x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x100x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x124x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x124x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x128x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x100x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x128x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x128x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x100x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x100x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x132x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x132x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x100x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x136x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x136x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x100x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x100x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x100x136x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x136x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x136x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x140x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x140x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x100x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x144x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x100x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x100x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x144x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x100x148x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x148x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x148x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x100x148x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x100x152x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x152x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x152x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x152x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x152x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x100x152x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x100x152x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x100x156x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x100x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x156x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x100x156x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x100x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x100x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x100x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x100x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x160x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x100x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x100x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x164x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x164x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x164x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x100x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x100x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x100x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x100x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x100x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x100x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x100x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x100x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x100x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x100x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x100x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x100x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x100x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x100x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x100x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x100x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:35
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x101x101x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x1023x1023x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1023x1023x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:248
2x256x1024x1024x1x1x1x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:256
2x256x1024x1024x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x256x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,8,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x1024x1024x1x3x3x1x12x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x1024x1024x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x1024x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x1024x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x1024x1024x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x1024x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1024x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x102x19x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x102x19x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x102x19x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x102x19x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:35
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,69[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x103x103x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x1040x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1040x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1040x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1040x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x104x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x104x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x104x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x104x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x104x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x104x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x104x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x104x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x104x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x104x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x104x80x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x104x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x104x80x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x104x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x104x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x104x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x104x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x104x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x104x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x104x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x104x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x104x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x104x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x104x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x104x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x104x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x104x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x104x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x104x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1053x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1053x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x105x105x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x105x105x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x105x105x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x105x105x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x105x105x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x105x105x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x105x105x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x105x19x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x105x19x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x105x19x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x105x19x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x1064x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1064x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1064x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1064x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x106x39x1x3x3x1x1x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x106x39x1x3x3x1x1x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x106x39x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x106x39x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1076x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1076x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1076x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1076x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x107x19x1x3x3x1x256x119x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x107x19x1x3x3x1x256x119x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x107x19x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x107x19x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x107x19x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x107x19x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x1087x799x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x1088x800x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x108x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x108x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x108x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x108x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x108x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x108x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x108x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x108x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x108x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x108x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x108x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x108x80x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x108x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x108x80x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x108x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x108x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x108x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x108x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x108x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x108x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x108x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x108x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x108x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x108x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x108x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x108x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x108x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x108x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x108x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x108x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x108x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x108x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x108x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x108x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x108x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,5,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x109x175x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x109x175x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,79[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x109x175x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x109x175x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x10x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x10x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x10x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x10x1x4x4x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x10x10x1x4x4x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x10x10x1x4x4x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x10x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x10x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x14x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x10x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x10x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x10x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x10x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x14x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x14x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x15x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x10x15x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x10x15x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x15x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x10x15x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x10x15x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x10x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x10x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x10x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x10x15x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x10x15x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x10x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x10x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x10x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x10x15x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x15x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x10x15x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x256x10x15x1x3x3x1x768x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x10x15x1x3x3x1x768x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x10x15x1x3x3x1x768x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x10x15x1x3x3x1x768x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x256x10x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x16x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x10x17x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x17x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x10x17x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x10x18x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x10x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x10x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x18x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x18x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x10x18x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x18x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x10x19x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x19x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x10x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x10x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x10x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x5x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x10x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x10x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x10x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x6x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x10x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x10x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x10x7x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x10x7x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x110x39x1x3x3x1x1x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x110x39x1x3x3x1x1x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x110x39x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x110x39x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x111x111x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x111x111x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x111x111x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x111x111x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x111x19x1x3x3x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x111x19x1x3x3x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x111x19x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x111x19x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x111x19x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x111x19x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x112x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x112x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x112x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x100x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x100x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x112x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x112x112x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3]
2x256x112x112x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x112x112x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x112x112x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x112x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3]
2x256x112x112x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x112x112x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x112x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x112x112x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3]
2x256x112x112x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x112x112x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x112x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:152
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x112x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x112x112x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x112x112x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 128, OddC, 32, 32, 2, 2, 16, 16, 16, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x112x112x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x112x112x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x112x112x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x112x112x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x112x112x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x112x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x112x112x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:134
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x112x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 128, OddC, 32, 32, 2, 2, 16, 16, 16, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x112x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x112x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x112x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x112x112x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x112x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x224x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x112x224x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x224x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Default, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x112x224x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x224x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x224x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+2
2x256x112x224x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x112x224x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x112x224x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x256x112x75x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x112x75x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x112x75x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x112x75x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x112x75x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x75x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x75x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x75x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x112x75x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x112x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x112x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x112x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x112x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x112x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x112x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x112x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x112x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x112x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x112x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x112x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x112x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x112x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x112x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x112x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x112x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x112x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x112x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x112x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x112x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1138x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1138x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1138x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1138x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x113x113x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x113x113x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x113x113x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x113x113x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x113x113x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x113x113x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x113x113x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x113x113x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x113x113x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x113x113x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x113x113x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x113x39x1x3x3x1x1x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x113x39x1x3x3x1x1x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x113x39x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x113x39x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x114x114x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x114x114x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x114x114x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x114x114x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x114x114x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x256x114x114x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x114x114x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x114x114x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x114x114x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x114x19x1x3x3x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x114x19x1x3x3x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x115x115x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x115x115x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x115x115x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x115x115x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x115x115x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x115x115x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x115x115x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x115x115x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x115x115x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x115x115x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x115x115x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x115x115x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x115x115x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x115x19x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x115x19x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x115x19x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x115x19x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x115x19x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x115x19x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x116x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x116x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x116x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x116x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x116x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x116x116x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x116x116x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x116x116x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x116x116x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x116x116x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x116x116x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x116x116x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+16
2x256x116x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x116x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x116x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x116x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x116x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x116x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x116x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x116x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x116x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x116x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x116x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x116x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x116x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x116x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x116x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x116x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x116x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x116x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x116x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x116x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x116x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x116x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x116x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x116x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x116x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x116x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x116x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x116x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x117x117x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x117x117x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x117x117x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x117x117x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1181x39x1x3x3x1x1x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1181x39x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x118x118x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x256x118x118x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x118x118x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+32
2x256x11x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x11x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x11x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x11x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x11x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x13x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x11x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x11x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x256x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x11x14x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x14x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[4];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x11x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x11x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x15x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x11x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x11x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x11x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x11x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x11x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x16x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x16x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x11x17x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x11x17x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x17x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x11x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x17x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x17x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x17x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x18x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x11x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x11x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x18x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x19x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x11x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x11x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x11x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x19x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x11x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x11x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x11x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x11x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x11x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x11x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x11x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x11x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x11x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x11x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x5x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x11x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x11x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x11x7x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x11x7x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x11x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x11x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x11x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x120x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x120x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x120x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x120x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x120x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,7,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x120x192x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x120x192x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x192x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x120x19x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x120x19x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x120x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x120x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x120x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x120x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x120x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x120x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x120x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x120x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x120x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x120x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x120x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x120x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x120x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x120x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x120x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,4,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x120x88x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x120x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x120x88x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x120x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x120x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x120x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x120x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x120x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x120x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x120x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x120x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x120x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x120x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x120x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x120x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x121x19x1x3x3x1x256x105x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x121x19x1x3x3x1x256x105x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x121x19x1x3x3x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x121x19x1x3x3x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x121x39x1x3x3x1x1x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x121x39x1x3x3x1x1x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x121x39x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x121x39x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x122x19x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x122x19x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x122x19x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x122x19x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x1231x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1231x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1231x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1231x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x123x19x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x123x19x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x123x39x1x3x3x1x1x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x123x39x1x3x3x1x1x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x123x39x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x123x39x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1246x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1246x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1246x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1246x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x124x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x124x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x124x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x124x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x124x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x124x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x80x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x124x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x124x80x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x124x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x124x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x124x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x124x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x124x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x124x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x124x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x124x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x124x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x124x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x124x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x124x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x92x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x92x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x124x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x124x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x124x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x124x96x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x124x96x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x125x125x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x125x125x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x125x19x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x125x19x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x125x19x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x125x19x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x1268x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1268x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1268x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1268x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x126x126x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x126x19x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x126x19x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x126x19x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x126x19x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x128x128x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128
2x256x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[1]
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Filter1x1Stride1Pad0, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x128x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x190x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x128x1x3x3x1x217x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x128x128x1x3x3x1x232x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x239x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x128x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x128x128x1x3x3x1x256x140x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x128x128x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+2
2x256x128x128x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+2
2x256x128x128x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x256x128x128x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x128x128x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+2
2x256x128x128x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+2
2x256x128x128x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x128x128x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+2
2x256x128x128x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x128x128x1x7x7x1x256x1x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x128x128x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x128x128x1x7x7x1x512x1x3x3x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x256x128x19x1x3x3x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x128x19x1x3x3x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x128x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x128x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x128x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x128x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x128x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x128x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x128x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x128x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x128x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x128x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x128x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x128x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x128x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x128x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x92x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x92x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x128x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x128x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x128x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x128x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x128x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x128x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x129x129x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x12x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x12x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x12x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x12x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x12x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x12x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x12x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x12x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x12x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x12x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x12x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x14x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x14x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x12x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x12x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x14x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x15x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x12x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x15x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x12x15x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x16x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x12x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x12x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x16x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x17x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x17x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x12x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x12x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x12x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x17x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x18x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x12x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x12x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x18x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x18x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x18x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x18x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x18x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x12x19x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x19x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x12x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x19x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x19x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x12x20x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x20x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x12x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x12x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x12x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x12x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x12x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x12x22x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x12x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x12x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x12x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x12x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x130x130x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x131x19x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x131x19x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x131x19x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x131x19x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x131x19x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x131x19x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x131x19x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x131x19x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x131x39x1x3x3x1x1x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x131x39x1x3x3x1x1x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x131x39x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x131x39x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x132x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x132x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x132x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x132x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x132x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x132x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x132x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x132x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x132x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x132x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x132x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x132x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x132x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x132x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x132x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x132x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x132x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x132x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x132x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x132x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x132x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x88x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x132x88x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x132x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x132x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x132x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x132x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x132x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x132x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x132x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x132x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x132x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x132x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x132x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x133x19x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x133x19x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x133x19x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x133x19x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x1343x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1343x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1343x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1343x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x134x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x134x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x134x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x134x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x134x19x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x134x19x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x134x19x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x134x19x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x135x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x135x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x135x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x135x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x1362x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1362x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1362x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1362x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x136x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x136x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x136x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x136x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x136x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x136x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x100x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x136x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x136x100x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x136x19x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x136x19x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x136x19x1x3x3x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x136x19x1x3x3x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x136x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x136x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x136x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x136x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x136x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x136x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x136x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x136x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x136x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x136x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x136x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x136x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x136x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x136x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x136x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x136x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x136x88x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x136x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x136x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x136x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x136x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x88x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x136x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x136x88x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x136x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x136x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x136x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x136x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x136x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x136x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x136x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x136x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x136x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x136x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x136x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x136x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x136x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1378x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1378x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1378x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1378x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x137x39x1x3x3x1x1x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x137x39x1x3x3x1x1x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x137x39x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x137x39x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x138x19x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x138x19x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x138x19x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x138x19x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x139x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x139x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x139x19x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x139x19x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x10x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x256x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x13x13x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x13x13x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x2048x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x2048x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x13x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x13x13x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x13x13x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x13x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,5,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,7,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x13x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x13x13x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x256x13x13x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x13x13x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x13x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x13x13x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x13x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x13x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x13x13x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x14x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x14x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x15x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x15x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x15x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x15x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x16x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x16x1x3x3x1x2048x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x16x1x3x3x1x2048x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x13x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x16x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x16x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x17x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x17x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x13x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x13x17x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x17x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x18x1x3x3x1x2048x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x18x1x3x3x1x2048x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x13x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x13x18x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x13x19x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x19x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x19x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x19x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x13x19x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x19x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x13x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x13x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x13x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x13x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x13x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x13x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x13x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x13x23x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x13x25x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x13x25x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x13x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x140x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x140x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x140x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x140x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x140x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x140x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x140x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x140x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x140x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x140x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x140x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x140x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x140x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x140x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x140x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x140x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x140x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x140x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x140x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x140x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x140x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x140x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x140x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x140x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x140x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x140x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x140x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x140x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x140x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x140x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x140x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x140x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x140x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x141x19x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x141x19x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x141x19x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x141x19x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x142x19x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x142x19x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x142x39x1x3x3x1x1x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x142x39x1x3x3x1x1x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,4,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x142x39x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x142x39x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x143x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x143x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x143x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x143x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x1443x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1443x39x1x3x3x1x1x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1443x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1443x39x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1444x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1444x39x1x3x3x1x1x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1444x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1444x39x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x144x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x144x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x144x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x144x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x144x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x144x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x144x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x144x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x144x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x144x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x144x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x144x19x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x144x19x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x256x144x336x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x336x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x144x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x144x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x144x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x144x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x144x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x144x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x144x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x144x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x144x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x144x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x144x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x144x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x92x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x144x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x144x92x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x144x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x144x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x144x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x144x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x144x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x144x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x144x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x144x96x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x144x96x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x144x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1463x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1463x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1463x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1463x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x146x19x1x3x3x1x256x67x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x146x19x1x3x3x1x256x67x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x147x147x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x147x19x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x147x19x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x148x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x148x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x148x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x148x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x148x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x148x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x148x148x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x148x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x148x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x148x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x148x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x19x1x3x3x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x148x19x1x3x3x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x148x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x148x19x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x148x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x148x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x148x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x148x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x148x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x148x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x148x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x148x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x148x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x148x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x148x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x148x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x148x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x148x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x148x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x148x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x148x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x148x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x148x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x148x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x148x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x148x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x148x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x148x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x148x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1496x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1496x39x1x3x3x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x1496x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1496x39x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x10x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x14x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x14x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x14x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x14x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x256x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x14x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x14x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x14x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x14x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x14x13x1x3x3x1x256x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x13x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:206
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:194
2x256x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:211
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:208
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:245
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:233
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:223
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:250
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:255
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:248
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:227
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x1280x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,190[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,97[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,3,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x608x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x2x2x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x101x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x101x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x102x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x102x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x103x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x103x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x106x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x106x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x107x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x107x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x108x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x108x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x109x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x109x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x113x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x113x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x115x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x115x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x117x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x117x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x121x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x121x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x123x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x123x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x125x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x125x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x126x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x126x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x127x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x127x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x130x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x130x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x132x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x132x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x133x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x133x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x134x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x134x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x135x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x135x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x136x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x136x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x138x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x138x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x139x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x139x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x140x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x140x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x141x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x141x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x142x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x142x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x144x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x144x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x146x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x146x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x148x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x148x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x149x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x149x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x151x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x151x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x152x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x152x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x153x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x153x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x154x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x154x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x156x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x156x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x159x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x159x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x160x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x160x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x161x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x161x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x162x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x162x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x164x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x164x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x165x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x165x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x166x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x166x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x167x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x167x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x168x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x168x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x169x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x169x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x173x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x173x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x174x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x174x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x176x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x176x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x178x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x178x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x180x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x180x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x184x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x184x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x185x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x185x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x186x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x186x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x188x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x188x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x191x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x191x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x192x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x192x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x194x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x194x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x195x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x195x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x196x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x196x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x197x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x197x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x2x2x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x202x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x202x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x207x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x207x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x210x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x210x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x211x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x211x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x212x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x212x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x213x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x213x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x214x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x214x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x215x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x215x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x216x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x216x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x219x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x219x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x220x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x220x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x221x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x221x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x225x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x225x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x227x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x227x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x228x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x228x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x229x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x229x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x231x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x231x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x232x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x232x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x233x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x233x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x234x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x234x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x236x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x236x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x238x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x238x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x240x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x240x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x243x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x243x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x244x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x244x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x245x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x245x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x247x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x247x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x248x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x248x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x249x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x249x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x250x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x250x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x254x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x254x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x255x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x255x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x256x14x14x1x2x2x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x78x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x78x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x2x2x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x81x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x81x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x2x2x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x2x2x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x2x2x1x256x89x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x89x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x91x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x2x2x1x256x91x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x2x2x1x256x92x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x92x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x93x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x93x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x2x2x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x2x2x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x2x2x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x2x2x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:2
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x14x14x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x190x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x14x14x1x3x3x1x214x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x225x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x14x14x1x3x3x1x232x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x101x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x101x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x101x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:252
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:129
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:73
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x14x14x1x3x3x1x256x102x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x102x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x102x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x103x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x103x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x103x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x104x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x104x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x104x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x106x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x106x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x106x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x109x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x109x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x109x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x110x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x110x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x110x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x111x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x111x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x111x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x113x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x113x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x113x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x115x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x115x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x115x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x117x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x117x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x117x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x122x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x122x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x122x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x123x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x123x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x123x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x124x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x124x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x124x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:234
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:229
2x256x14x14x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:212
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:200
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:201
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:76
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:205
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:69
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x129x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x129x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x129x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x130x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x130x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x130x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x131x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x131x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x131x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x132x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x132x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x132x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x133x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x133x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x133x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x136x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x136x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x136x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x137x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x137x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x137x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x138x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x138x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x138x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x139x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x139x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x139x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x141x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x141x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x141x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x142x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x142x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x142x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x143x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x143x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x143x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x144x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x144x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x144x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x145x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x145x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x145x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x146x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x146x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x146x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x147x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x147x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x147x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x148x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x148x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x148x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x149x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x149x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x149x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x151x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x151x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x151x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x153x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x153x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x153x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x154x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x154x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x154x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x155x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x155x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x155x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x156x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x156x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x156x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x158x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x158x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x158x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x159x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x159x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x159x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:102
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:128
2x256x14x14x1x3x3x1x256x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:75
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:192
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:192
2x256x14x14x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x256x14x14x1x3x3x1x256x160x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x160x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x160x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x162x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x162x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x162x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x163x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x163x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x163x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x164x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x164x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x164x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x166x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x166x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x166x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x168x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x168x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x168x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x169x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x169x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x169x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;TransposedConvBinWinoRxS<3-2>:246
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:231
2x256x14x14x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:128
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:116
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:110
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:66
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:118
2x256x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:76
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x171x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x171x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x171x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x174x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x174x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x174x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x175x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x175x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x175x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x176x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x176x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x176x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x179x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x179x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x179x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x181x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x181x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x181x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x182x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x182x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x182x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x186x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x186x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x186x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x189x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x189x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x189x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x190x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x190x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x190x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x191x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x191x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x191x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x194x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x194x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x194x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x195x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x195x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x195x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x197x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x197x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x197x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x201x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x201x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x201x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x202x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x202x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x202x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x205x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x205x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x205x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x206x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x206x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x206x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x207x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x207x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x207x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:243
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:239
2x256x14x14x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:227
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:218
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:236
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:85
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:222
2x256x14x14x1x3x3x1x256x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:76
2x256x14x14x1x3x3x1x256x210x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x210x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x210x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x211x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x211x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x211x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x212x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x212x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x212x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x214x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x214x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x214x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x216x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x216x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x216x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x217x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x217x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x217x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x218x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x218x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x218x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x220x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x220x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x220x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x222x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x222x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x222x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x223x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x223x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x223x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x224x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x224x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x224x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x226x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x226x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x226x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x227x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x227x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x227x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x228x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x228x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x228x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x229x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x229x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x229x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x230x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x230x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x230x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x231x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x231x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x231x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x232x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x232x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x232x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x234x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x234x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x234x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x235x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x235x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x235x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x236x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x236x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x236x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x237x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x237x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x237x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x240x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x240x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x240x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x241x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x241x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x241x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x242x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x242x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x242x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x243x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x243x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x243x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x244x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x244x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x244x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x245x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x245x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x245x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x246x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x246x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x246x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x248x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x248x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x248x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x249x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x249x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x249x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x254x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x254x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x254x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x255x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x255x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x255x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:254
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:247
2x256x14x14x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:232
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:230
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:69
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:230
2x256x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:67
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x3x3x1x256x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:245
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:246
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:91
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:77
2x256x14x14x1x3x3x1x256x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:204
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:200
2x256x14x14x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:202
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:237
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:76
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:209
2x256x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:66
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:239
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:75
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:232
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:236
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:224
2x256x14x14x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x256x14x14x1x3x3x1x256x38x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x38x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x38x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x39x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x39x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x39x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x14x14x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:78
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:97
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:245
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15
2x256x14x14x1x3x3x1x256x41x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x41x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x41x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x44x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x44x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x44x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x45x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x45x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x45x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x46x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x46x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x46x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x49x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x49x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x49x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:248
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x256x14x14x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:247
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:250
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:116
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:249
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:69
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:194
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:65
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:160
2x256x14x14x1x3x3x1x256x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:94
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:217
2x256x14x14x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x256x14x14x1x3x3x1x256x52x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x52x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x52x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x53x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x53x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x53x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x60x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x60x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x60x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x61x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x61x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x61x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:254
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:240
2x256x14x14x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:131
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];TransposedConvBinWinoRxS<3-2>:244
2x256x14x14x1x3x3x1x256x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:156
2x256x14x14x1x3x3x1x256x62x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x62x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x62x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x63x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x63x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x63x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:218
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:200
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:222
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:245
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:208
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:68
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:206
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:66
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x65x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x65x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x65x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x66x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x66x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x66x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x67x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x67x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x67x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x72x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x72x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x72x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x73x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x73x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x73x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x76x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x76x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x76x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x77x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x77x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x77x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x78x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x78x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x78x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x79x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x79x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x79x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x14x14x1x3x3x1x256x80x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x80x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x80x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x82x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x82x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x82x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x83x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x83x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x83x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x85x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x85x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x85x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x87x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x87x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x87x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x88x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x88x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x88x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x89x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x89x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x89x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];TransposedConvBinWinoRxS<3-2>:119
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:113
2x256x14x14x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:58
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:72
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:79
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:71
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:57
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:81
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x14x1x3x3x1x256x90x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x90x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x90x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x91x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x91x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x91x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x93x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x14x14x1x3x3x1x256x93x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x93x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x94x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x14x14x1x3x3x1x256x94x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x94x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x97x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x14x14x1x3x3x1x256x97x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x97x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x256x98x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x14x14x1x3x3x1x256x98x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x256x98x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x14x14x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:17
2x256x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x14x1x7x7x1x256x1x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x14x14x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x14x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x16x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x17x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x14x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x18x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x14x18x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x18x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x14x20x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x14x20x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x14x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x20x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x14x20x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x14x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x21x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x14x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x14x22x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x151x151x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x151x151x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x151x19x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x151x19x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x152x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x152x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x152x100x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x152x100x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x152x100x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x152x152x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x152x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x152x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x152x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x152x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x152x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x152x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x152x19x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x152x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x152x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x152x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x152x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x152x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x152x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x152x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x152x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x152x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x152x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x152x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x152x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x152x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x96x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x152x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x152x96x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x152x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x152x96x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x152x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x1536x1536x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1536x1536x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1536x1536x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x1536x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1536x1536x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1]
2x256x1536x1536x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x153x153x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x153x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x153x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x153x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x153x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x153x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x153x19x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x153x19x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x153x19x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x153x19x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x153x39x1x3x3x1x1x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x153x39x1x3x3x1x1x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x153x39x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x153x39x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x154x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x154x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x154x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x154x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x155x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x155x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x155x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x155x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x155x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x155x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x155x39x1x3x3x1x1x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x155x39x1x3x3x1x1x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x155x39x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x155x39x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x156x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x156x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x156x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x156x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x156x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x156x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x156x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x156x19x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x156x19x1x3x3x1x256x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x156x19x1x3x3x1x256x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x156x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x156x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x156x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x156x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x156x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x156x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x156x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x156x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x156x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x156x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x156x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x156x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x156x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x156x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x156x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x156x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x156x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x156x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x156x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x156x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x156x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x156x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x156x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x157x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x157x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x158x39x1x3x3x1x1x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x158x39x1x3x3x1x1x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x158x39x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x158x39x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x159x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x159x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x159x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x159x207x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x159x207x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x159x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x159x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x159x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x159x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x159x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x159x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x15x10x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x15x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x15x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x15x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x15x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x15x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x15x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x15x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x15x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x15x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x15x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x15x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x15x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x15x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x13x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x15x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x15x15x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x15x15x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x15x15x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x15x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x15x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x15x15x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x15x15x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x15x15x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x15x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x15x15x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x15x15x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x15x15x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x15x15x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x15x15x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x15x15x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x15x15x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x15x15x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x15x15x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x15x15x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x15x15x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x15x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x15x17x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x19x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x20x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x256xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x15x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x15x21x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x15x21x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x15x21x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x15x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x160x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x160x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x160x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x160x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x160x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x160x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x160x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x160x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x160x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x160x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x160x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x160x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x160x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x160x19x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x160x208x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x208x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x208x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x160x216x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x160x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x216x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x216x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x216x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x160x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x224x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x160x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x160x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x240x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x160x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x240x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x160x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x160x248x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x160x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x248x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x256x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x160x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x160x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x160x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x160x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x272x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x160x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x160x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x288x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x288x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x288x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x160x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x160x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x160x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x160x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x160x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x160x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x160x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x160x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x160x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x160x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x160x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x160x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x160x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x161x19x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x161x19x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x161x19x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x161x19x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x162x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x162x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x162x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x162x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x162x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x162x19x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x163x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x163x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x163x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x163x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x163x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x163x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x163x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x163x19x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x163x39x1x3x3x1x1x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x163x39x1x3x3x1x1x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x163x39x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x163x39x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x164x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x164x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x164x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x164x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x164x19x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x164x19x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x164x19x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x164x19x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x164x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x164x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x164x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x164x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x164x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x164x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x164x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x164x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x164x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x164x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x164x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x164x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x164x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x164x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x164x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x164x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x164x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x164x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x164x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x164x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x165x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x165x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x165x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x165x19x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x166x19x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x166x19x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x166x19x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x166x19x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x167x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x167x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x167x19x1x3x3x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x167x19x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x167x19x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x167x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x167x19x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x167x207x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x207x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x167x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x167x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x167x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x167x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x167x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x167x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x167x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x168x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x100x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x168x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x168x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x208x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x208x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x208x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x168x208x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x216x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x216x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x168x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x224x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x224x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x168x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x168x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x232x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x232x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x248x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x256x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x256x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x168x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x168x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x272x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x280x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x168x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x168x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x296x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x296x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x168x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x304x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x304x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x168x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x312x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x312x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x320x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x320x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x168x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x168x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x168x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x168x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x168x328x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x168x336x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x336x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x336x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x168x39x1x3x3x1x1x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x168x39x1x3x3x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x168x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x168x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x168x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x168x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x168x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x168x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x168x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x168x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x168x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x168x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x88x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x168x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x168x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x168x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x168x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x168x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x168x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x168x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x168x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x168x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x168x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x168x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x168x96x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x168x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x16x10x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x16x10x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x16x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x16x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x16x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x16x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x16x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x16x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x16x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x16x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x16x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x16x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x12x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x16x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x16x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x16x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x16x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x16x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x16x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x16x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x16x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x16x16x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x16x16x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x16x16x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x16x16x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x16x16x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x16x16x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x16x16x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x16x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x16x16x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x16x16x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x256x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x16x16x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x16x16x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x16x16x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x16x16x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x16x16x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x16x16x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x16x16x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x16x16x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x16x16x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x16x16x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x16x16x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x16x16x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x16x16x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x16x16x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x170x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x170x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x170x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x170x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x171x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x171x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x171x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x171x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x171x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x171x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x171x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x171x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x171x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x171x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x171x39x1x3x3x1x1x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x171x39x1x3x3x1x1x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x171x39x1x3x3x1x1x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x171x39x1x3x3x1x1x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x171x39x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x171x39x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x171x39x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x171x39x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x174x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x174x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x174x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x174x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x174x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x174x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x174x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x174x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x174x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x174x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x175x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x175x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x175x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x175x19x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x175x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x175x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x175x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x175x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x176x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x176x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x216x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x216x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x176x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x176x216x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x176x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x176x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x176x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x232x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x232x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x240x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x240x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x176x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x176x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x248x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x176x256x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x264x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x264x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x280x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x176x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x176x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x176x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x296x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x176x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x304x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x304x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x176x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x312x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x312x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x176x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x176x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x320x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x176x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x176x328x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x176x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x176x336x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x176x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x177x19x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x177x19x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x177x19x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x177x19x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x178x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x178x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x178x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x178x19x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x178x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x178x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x178x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x178x19x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x178x39x1x3x3x1x1x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x178x39x1x3x3x1x1x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x178x39x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x178x39x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x17x10x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x10x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x17x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x17x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x17x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x17x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x17x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x17x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x17x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x17x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x13x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x1x7x1x224x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x1x7x1x256x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x17x1x1x7x1x256x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x1x7x1x256x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x256x17x17x1x1x7x1x256x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x1x7x1x256x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x1x7x1x256x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x1x7x1x256x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x17x17x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[5];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x17x17x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x17x17x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x17x17x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x17x17x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x17x17x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x17x17x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+2
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x3x3x1x224x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x3x3x1x224x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x17x17x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x17x17x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x17x17x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x17x17x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x17x17x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x3x3x1x256x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x3x3x1x320x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x7x1x1x224x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x7x1x1x224x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x7x1x1x224x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x17x17x1x7x1x1x224x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x7x1x1x224x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x17x17x1x7x1x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x7x1x1x224x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x17x17x1x7x1x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x17x17x1x7x1x1x224x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x7x1x1x224x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x7x1x1x224x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x17x17x1x7x1x1x224x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x17x17x1x7x1x1x224x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x7x1x1x224x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x17x17x1x7x1x1x224x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x17x17x1x7x1x1x224x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x17x17x1x7x1x1x224x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x17x17x1x7x1x1x320x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x17x17x1x7x1x1x320x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x7x1x1x320x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x7x1x1x320x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x7x1x1x320x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x7x1x1x320x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x7x1x1x320x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x17x1x7x1x1x320x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x7x1x1x320x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x7x1x1x320x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x7x1x1x320x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x7x1x1x320x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x17x17x1x7x1x1x320x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x7x1x1x320x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x17x17x1x7x1x1x320x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x17x17x1x7x1x1x320x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x17x1x7x1x1x320x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x81x1x5x5x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x81x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x17x81x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x17x81x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x17x81x1x5x5x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x17x81x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x1808x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1808x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1808x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1808x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x180x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x180x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x180x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x180x19x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1824x2288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1824x2288x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1824x2288x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x182x19x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x182x19x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x182x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x182x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x182x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x182x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x183x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x183x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x183x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x183x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x183x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x183x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x183x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x183x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x183x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x183x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x183x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x183x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x1840x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1840x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1840x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1840x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x184x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x184x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x184x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x184x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x184x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x184x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x232x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x232x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x184x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x184x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x240x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x184x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x248x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x184x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x248x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x272x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x184x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x280x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x280x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x280x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x288x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x296x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x296x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x296x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x184x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x304x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x312x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x184x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x184x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x320x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x184x328x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x184x328x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x328x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x184x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x184x328x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x184x336x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x336x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x184x336x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x184x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x184x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x184x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x184x39x1x3x3x1x256x150x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x184x39x1x3x3x1x256x150x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x186x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x186x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x186x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x186x19x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x187x19x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x187x19x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x187x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x187x19x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x188x19x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x188x19x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x188x19x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x188x19x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x188x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x188x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x188x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x188x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x189x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x189x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x189x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x189x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x18x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x18x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x18x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x18x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x18x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x18x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x18x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x18x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x18x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x18x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x12x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x18x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x18x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x13x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x18x18x1x3x3x1x224x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x18x18x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x18x18x1x3x3x1x224x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x18x18x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x18x18x1x3x3x1x224x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x18x18x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x256x18x18x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x18x18x1x3x3x1x224x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x18x18x1x3x3x1x224x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x18x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x18x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x18x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x82x1x5x5x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x82x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x18x82x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x82x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x82x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x82x1x5x5x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x18x82x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x18x86x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x18x86x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x18x86x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x18x86x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x18x86x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x18x86x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x18x86x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x18x86x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x18x86x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x18x86x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x18x86x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x18x86x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x190x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x190x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x190x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x190x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x191x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x191x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x207x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x207x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x191x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x191x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x191x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x192x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x192x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x192x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x208x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x208x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x208x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x208x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x192x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x192x208x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x216x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x216x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x224x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x192x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x232x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x232x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x240x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x248x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x192x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x248x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x192x248x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x192x248x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x256x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x192x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x192x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x280x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x192x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x192x280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x192x288x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x288x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x296x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x296x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x192x296x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x304x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x192x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x312x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x312x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x192x312x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x192x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x320x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x320x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x320x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x192x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x192x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x192x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x328x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x192x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x336x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x192x336x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x192x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x192x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x192x336x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x193x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x193x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x193x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x193x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x193x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x193x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x193x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x193x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x193x39x1x3x3x1x1x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x193x39x1x3x3x1x1x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x193x39x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x193x39x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x194x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x194x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x194x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x194x19x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x194x39x1x3x3x1x1x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x194x39x1x3x3x1x1x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x194x39x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x194x39x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x195x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x195x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x195x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x195x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x197x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x197x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x197x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x197x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x197x39x1x3x3x1x1x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x197x39x1x3x3x1x1x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x197x39x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x197x39x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x199x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x199x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x199x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x199x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x199x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x199x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x199x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x199x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x199x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x199x19x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x199x215x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x215x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x231x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x231x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x239x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x239x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x247x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x247x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x263x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x263x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x271x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x271x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x271x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x271x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x279x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x287x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x287x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x295x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x295x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x303x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x303x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x303x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x303x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x311x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x311x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x319x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x199x319x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x327x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x327x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x335x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x199x335x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x199x39x1x3x3x1x1x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x199x39x1x3x3x1x1x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x199x39x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x199x39x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x19x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x19x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x19x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x19x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x19x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x19x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x19x12x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x19x12x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x19x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x19x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x19x13x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x19x13x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x13x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:254
2x256x19x19x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:130
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:128
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];TransposedConvBinWinoRxS<2-3>:131;TransposedConvBinWinoRxS<3-2>:196
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:253
2x256x19x19x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:130
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:243
2x256x19x19x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:129
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:210
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:170;TransposedConvBinWinoRxS<3-2>:129
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:214
2x256x19x19x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:130
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:251
2x256x19x19x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:128
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];TransposedConvBinWinoRxS<3-2>:88
2x256x19x19x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:135;TransposedConvBinWinoRxS<3-2>:159
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:216
2x256x19x19x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:156;TransposedConvBinWinoRxS<3-2>:141
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:86
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:135;TransposedConvBinWinoRxS<3-2>:138
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];TransposedConvBinWinoRxS<3-2>:86
2x256x19x19x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:163;TransposedConvBinWinoRxS<3-2>:141
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:123
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:134
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:242
2x256x19x19x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:142;TransposedConvBinWinoRxS<3-2>:129
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+32
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:238
2x256x19x19x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:138;TransposedConvBinWinoRxS<3-2>:136
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:249
2x256x19x19x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:158
2x256x19x19x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x19x19x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x19x19x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x19x19x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x19x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x19x19x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x19x19x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x19x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x19x19x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x19x19x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x19x19x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x19x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x19x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:243
2x256x19x19x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:246
2x256x19x19x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x19x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:228
2x256x19x19x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:44
2x256x19x19x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x19x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:42
2x256x19x19x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x19x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:236
2x256x19x19x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x19x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x19x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x19x19x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x28x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x19x28x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x19x28x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x19x28x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x28x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x19x28x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x19x28x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x28x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x28x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x19x83x1x5x5x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x83x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x83x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x19x83x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x83x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x19x83x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x83x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x19x83x1x5x5x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x19x83x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x19x83x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x19x83x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x19x83x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x19x83x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x19x87x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x19x87x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x19x87x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x19x87x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x19x87x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x19x87x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x1024x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x1024x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x128x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x19x88x1x5x5x1x128x16x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x19x88x1x5x5x1x128x1x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x256x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x19x88x1x5x5x1x128x2x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x19x88x1x5x5x1x128x32x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x19x88x1x5x5x1x128x4x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x512x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x512x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x19x88x1x5x5x1x128x64x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x19x88x1x5x5x1x128x8x1x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x1x1x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x1x1x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x1x1x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+8
2x256x1x1x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+8
2x256x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x1x1x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x1x1x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:38
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:33
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16;TransposedConvBinWinoRxS<3-2>:63
2x256x1x1x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2;TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:34
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:27
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:136;TransposedConvBinWinoRxS<3-2>:47
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x1x1x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:19
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:75
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x1x1x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:9
2x256x1x1x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:232;TransposedConvBinWinoRxS<3-2>:37
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:35
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:132;TransposedConvBinWinoRxS<3-2>:44
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[1];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:253;TransposedConvBinWinoRxS<3-2>:33
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:249;TransposedConvBinWinoRxS<3-2>:167
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:88
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1;TransposedConvBinWinoRxS<2-3>:132;TransposedConvBinWinoRxS<3-2>:32
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x1x1x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x1x1x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x1x1x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x1x1x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x1x1x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x324x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x1x1x1x7x7x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x7x7x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x7x7x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x7x7x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x7x7x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x7x7x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x7x7x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x7x7x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x7x7x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x1x1x1x7x7x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x1x1x1x7x7x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x200x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x200x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x200x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x200x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x200x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x200x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x200x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x200x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x200x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x200x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x200x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x200x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x200x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x216x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x216x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x224x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x224x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x200x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x200x224x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x232x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x232x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x200x232x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x240x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x240x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x240x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x240x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x248x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x248x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x256x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x200x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x264x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x264x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x264x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x264x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x200x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x200x272x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x272x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x200x272x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x200x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x200x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x200x280x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x280x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x280x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x280x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x288x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x288x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x288x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x288x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x296x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x296x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x296x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x304x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x304x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x200x304x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x200x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x200x304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x200x312x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x312x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x312x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x312x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x200x312x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x200x320x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x320x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x320x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x200x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x200x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x200x320x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x200x328x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x200x328x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x328x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x200x328x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x200x336x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x336x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x200x336x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x200x336x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x201x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x201x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x201x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x201x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x201x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x201x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x201x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x201x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x202x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x202x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x202x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x202x19x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2032x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2032x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2032x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2032x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2032x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2032x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2032x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x203x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x203x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x203x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x203x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x2048x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x2048x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x2048x2048x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106
2x256x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 256, 128, 64, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100
2x256x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x2048x1x3x3x1x12x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x2048x2048x1x3x3x1x12x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x256x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x256x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x2048x2048x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x2048x2048x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x2048x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2048x2048x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1]
2x256x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x256x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x204x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x204x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x204x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x204x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x205x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x205x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x205x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x205x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x205x19x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x205x19x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x205x19x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x205x19x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x205x39x1x3x3x1x1x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x205x39x1x3x3x1x1x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x205x39x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x205x39x1x3x3x1x256x158x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2064x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2064x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2064x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2064x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2064x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2064x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x207x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x207x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x207x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x207x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x160x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x208x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x160x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x208x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x208x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x208x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x208x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x208x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x208x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x208x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x208x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x208x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x208x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x208x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x208x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x208x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x208x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x208x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x208x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x208x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x208x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x208x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x208x19x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x208x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x208x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x209x209x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x209x209x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x256x209x209x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x209x209x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x209x209x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x209x209x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x256x20x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x20x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x20x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x12x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x12x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x13x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x20x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x13x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x20x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x20x20x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x20x20x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x20x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x20x20x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x20x20x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x20x20x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x20x20x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x20x20x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x20x20x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x20x20x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x20x20x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x20x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x20x20x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x20x20x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x20x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x20x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x20x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x20x20x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x20x20x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x20x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x20x20x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x20x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x20x20x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x20x20x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x26x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x20x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x20x26x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x27x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x20x27x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x20x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x20x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x27x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x27x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x27x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x28x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x20x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x28x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x20x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x28x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x29x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x20x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x20x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x20x30x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x30x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x30x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x30x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x30x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x20x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x31x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x31x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x31x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x32x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x33x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x33x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x20x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x20x34x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x20x34x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x20x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x36x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x20x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x20x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x36x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x256x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x36x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x36x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x36x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x20x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x20x38x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x20x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x39x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x20x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x41x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x20x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x41x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x20x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x20x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x20x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x84x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x20x84x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x84x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x84x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x84x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x20x84x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x20x84x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x20x84x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x84x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x84x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x20x84x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x20x84x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x84x1x5x5x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x20x84x1x5x5x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x5x5x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x20x84x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x5x5x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x5x5x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x20x84x1x5x5x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x20x84x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x20x84x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x20x84x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x84x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x20x84x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x20x88x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x20x88x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x88x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x20x88x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x20x88x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x20x88x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x20x88x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x20x88x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x20x88x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x20x88x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x20x88x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x20x88x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x210x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x210x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x210x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x210x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x210x210x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x210x210x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7]
2x256x210x210x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x210x210x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x256x210x210x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x210x210x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x210x210x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x210x210x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x211x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x211x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x211x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x211x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x211x211x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x211x211x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x211x39x1x3x3x1x1x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x211x39x1x3x3x1x1x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x211x39x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x211x39x1x3x3x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x212x212x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x212x212x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x212x212x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x212x212x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x213x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x213x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x213x213x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x213x213x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x213x213x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x213x213x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x215x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x215x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x215x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x215x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x215x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x215x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x215x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x215x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x215x39x1x3x3x1x1x119x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x215x39x1x3x3x1x1x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x215x39x1x3x3x1x1x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x215x39x1x3x3x1x256x119x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x215x39x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x215x39x1x3x3x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x216x160x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x216x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x216x160x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x216x160x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x216x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x216x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x216x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x216x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x216x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x216x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x216x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x216x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x216x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x216x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x216x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x216x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x216x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x216x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x216x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x216x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x216x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x216x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x218x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x218x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x218x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x218x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x218x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x218x19x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x21x10x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x10x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x10x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x11x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x11x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x21x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x21x11x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x12x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x13x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x13x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x21x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x21x15x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x15x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x21x15x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x21x15x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x21x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x15x1x3x3x1x320x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x21x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x21x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x21x21x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x21x21x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x21x21x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x21x21x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x21x21x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x21x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x21x21x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x21x21x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x21x21x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x21x21x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x21x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x21x21x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x21x21x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x21x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x21x21x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x21x21x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x21x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x21x21x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x21x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x21x21x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x21x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x26x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x26x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x21x26x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x21x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x26x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x26x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x27x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x27x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x21x28x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x21x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x21x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x21x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x21x28x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x21x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x28x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x28x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x21x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x29x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x29x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x21x29x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x30x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x21x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x21x30x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x21x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x30x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x21x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x31x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x21x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x32x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x32x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x21x33x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x21x34x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x35x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x21x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x21x35x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x21x35x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x36x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x21x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x37x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x21x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x37x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x37x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x37x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x38x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x21x38x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x38x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x21x39x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x21x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x21x41x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x41x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x21x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x21x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x21x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x21x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x85x1x5x5x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x21x85x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x85x1x5x5x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x21x85x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x21x85x1x5x5x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x21x85x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x21x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x220x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x220x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x220x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x220x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x220x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x220x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x220x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x220x19x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x221x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x221x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x221x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x221x19x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x222x19x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x222x19x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x222x19x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x222x19x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x223x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x199x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x199x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x223x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x223x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x223x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x223x223x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x223x223x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x223x223x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x112x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x224x112x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x256x224x112x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Default, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x224x112x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x224x112x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x224x112x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+2
2x256x224x112x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x224x112x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x224x112x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x256x224x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x224x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x224x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x224x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x224x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x224x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x224x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x224x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x224x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x224x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x224x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x224x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x224x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x224x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x224x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x224x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x224x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x224x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x224x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x224x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x224x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x224x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x224x200x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x224x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x224x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x224x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x224x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x224x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x224x224x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x224x224x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x224x224x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x224x39x1x3x3x1x1x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x224x39x1x3x3x1x1x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x224x39x1x3x3x1x1x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x224x39x1x3x3x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x224x39x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x224x39x1x3x3x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x225x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x225x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x225x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x225x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x225x225x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x225x225x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x226x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x226x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x226x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x226x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x2272x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2272x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2272x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2272x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x227x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x227x19x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x227x227x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x227x227x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x227x227x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2288x1824x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2288x1824x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2288x1824x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x228x228x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x228x228x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x229x229x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x229x229x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x229x229x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x229x229x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x229x229x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x22x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x22x11x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x22x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x22x12x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x22x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x22x14x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x22x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x22x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x22x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x22x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x22x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x22x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x22x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x22x27x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x22x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x27x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x22x27x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x27x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x22x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x28x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x29x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x22x29x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x30x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x22x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x22x30x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x22x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x22x30x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x30x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x30x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x31x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x31x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x31x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x32x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x33x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x22x33x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x22x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x22x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x22x33x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x33x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x33x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x34x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x34x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x34x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x34x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x22x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x22x35x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x22x36x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x36x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x37x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x37x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x37x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x22x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x22x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x38x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x39x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x39x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x22x39x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x22x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x22x41x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x22x41x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x41x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x22x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x22x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x2304x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x2304x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x230x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x230x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x230x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x230x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x230x39x1x3x3x1x1x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x230x39x1x3x3x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x231x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x231x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x231x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x231x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x231x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x231x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x232x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x232x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x232x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x232x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x232x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x232x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x232x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x232x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x232x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x232x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x232x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x232x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x232x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x232x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x232x39x1x3x3x1x1x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x232x39x1x3x3x1x1x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x232x39x1x3x3x1x1x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x232x39x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x232x39x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x232x39x1x3x3x1x256x94x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x233x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x233x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x233x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x233x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x234x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x234x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x234x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x234x19x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x235x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x235x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x235x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x235x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x237x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x237x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x237x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x237x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x238x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x238x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x238x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x238x19x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x239x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x239x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x239x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x239x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x239x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x239x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x239x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x239x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x23x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x23x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x23x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x23x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x23x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x23x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x23x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x27x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x27x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x23x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x28x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x23x28x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x28x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x23x29x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x23x29x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x29x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x29x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x30x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x30x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x30x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x30x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x31x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x23x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x23x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x23x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x23x31x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x31x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x31x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x31x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x31x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x23x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x32x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x32x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x23x33x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x33x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x34x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x34x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x34x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x35x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x35x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x23x35x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x23x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x23x35x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x23x35x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x35x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x35x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x36x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x36x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x36x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x37x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x23x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x37x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x37x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x37x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x38x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x23x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x23x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x38x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x38x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x39x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x39x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x39x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x23x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x23x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x23x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x23x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x23x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x23x41x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x41x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x23x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x23x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x23x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x23x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x23x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x23x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x23x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x240x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x240x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x240x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x240x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x240x176x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x240x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x240x176x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x240x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x240x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x240x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x240x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x240x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x240x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x240x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x240x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x240x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x240x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x240x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x240x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x240x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x240x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x240x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x240x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x240x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x240x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x241x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x241x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x241x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x241x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x241x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x241x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x241x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x241x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x241x39x1x3x3x1x1x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x241x39x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x243x39x1x3x3x1x1x105x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x243x39x1x3x3x1x1x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x243x39x1x3x3x1x256x105x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x243x39x1x3x3x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x246x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x246x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x246x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x246x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x246x39x1x3x3x1x1x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x246x39x1x3x3x1x1x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x246x39x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x246x39x1x3x3x1x256x97x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x247x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x247x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x247x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x247x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x247x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x247x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x247x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x247x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x247x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x247x39x1x3x3x1x1x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x247x39x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x248x160x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x248x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x160x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x248x160x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x248x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x248x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x248x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x248x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x248x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x248x184x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x248x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x184x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x192x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x192x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x248x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x248x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x248x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x248x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x248x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x248x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x248x19x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x248x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x248x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x248x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x248x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x248x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x248x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x248x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x24x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x24x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x24x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x24x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x24x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x24x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x24x24x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x24x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x24x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x24x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x24x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x24x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x24x26x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x24x26x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x26x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x26x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x27x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x24x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x27x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x24x27x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x28x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x24x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x28x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x29x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x24x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x24x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x24x29x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x29x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x29x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x30x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x24x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x30x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x30x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x30x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x31x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x24x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x24x31x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x24x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x24x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x24x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x24x32x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x32x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x32x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x33x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x24x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x33x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x33x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x34x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x24x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x34x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x24x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x35x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x36x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x24x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x24x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x36x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x36x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x36x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x24x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x37x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x37x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x37x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x38x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x38x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x38x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x39x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x39x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x39x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x39x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x39x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x39x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x24x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x40x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x24x40x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x24x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x24x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x40x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x40x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x24x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x41x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x41x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x24x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x24x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x24x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x24x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x24x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x24x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x24x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x250x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x250x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x250x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x250x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x251x19x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x251x19x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x251x19x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x251x19x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x251x39x1x3x3x1x1x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x251x39x1x3x3x1x1x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x251x39x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x251x39x1x3x3x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x253x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x253x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x253x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x253x19x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x253x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x253x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x253x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x253x19x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x253x253x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x253x253x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x253x39x1x3x3x1x1x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x253x39x1x3x3x1x1x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x253x39x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x253x39x1x3x3x1x256x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x254x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x254x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x254x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x254x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x255x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x255x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x255x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x255x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x255x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x255x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x255x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x255x255x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x255x255x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x255x255x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x255x255x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x255x255x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x255x255x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x2560x2560x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x256x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x256x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x256x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x256x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x256x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x256x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x256x184x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x184x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x256x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x256x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x256x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x256x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x256x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x256x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x256x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x256x256x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x156x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x256x256x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[7]
2x256x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x256x256x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[3]
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10]
2x256x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x256x256x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[1]
2x256x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x256x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x256x256x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,10
2x256x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3]
2x256x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x256x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10]
2x256x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x256x256x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2]
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[8]
2x256x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x256x256x1x1x1x1x728x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x256x256x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x256x256x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x256x256x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x256x256x1x3x3x1x44x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x256x256x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x256x256x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x256x256x1x5x5x1x256x4x2x2x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x257x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x257x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x257x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x257x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x257x257x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x257x257x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x257x257x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x258x39x1x3x3x1x1x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x258x39x1x3x3x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x25x13x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x25x13x1x3x3x1x224x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x25x13x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x25x13x1x3x3x1x224x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x25x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x25x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x25x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x25x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x25x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x25x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x25x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x25x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x25x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x28x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x25x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x28x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x28x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x29x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x29x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x29x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x31x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x25x31x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x25x32x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x32x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x32x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x25x33x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x25x33x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x33x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x25x34x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x25x34x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x34x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x34x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x34x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x35x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x35x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x35x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x36x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x37x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x37x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x37x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x38x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x38x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x25x38x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x25x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x25x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x25x38x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x38x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x39x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x25x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x25x39x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x39x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x39x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x25x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x25x41x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x25x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x25x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x41x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x41x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x41x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x25x41x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x25x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x25x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x25x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x25x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x25x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x25x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x260x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x260x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x260x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x260x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x260x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x260x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x260x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x260x19x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x262x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x262x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x262x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x262x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x263x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x263x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x263x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x263x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x263x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x263x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x263x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x263x39x1x3x3x1x1x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x263x39x1x3x3x1x1x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x263x39x1x3x3x1x1x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x263x39x1x3x3x1x1x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x263x39x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x263x39x1x3x3x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x263x39x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x263x39x1x3x3x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x264x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x264x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x264x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x264x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x264x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x264x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x264x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x264x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x264x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x264x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x264x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x264x176x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x264x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x264x176x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x264x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x264x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x264x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x264x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x264x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x264x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,32,32,32,2,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,16,1,4,2,1,1,8,1,16,36;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x264x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x264x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x264x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x264x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x264x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x264x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x264x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x264x19x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x264x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x264x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x264x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x264x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x264x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x264x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x267x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x267x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x267x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x267x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x267x39x1x3x3x1x1x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x267x39x1x3x3x1x1x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x267x39x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x267x39x1x3x3x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x269x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x269x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x269x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x269x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x269x39x1x3x3x1x1x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x269x39x1x3x3x1x1x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x269x39x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x269x39x1x3x3x1x256x77x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x26x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x26x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x26x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x26x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x26x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x26x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x26x20x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x20x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x26x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x26x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x26x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x26x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x26x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x26x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x26x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x26x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x26x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x26x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x26x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x26x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x26x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x26x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x26x26x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x26x26x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x26x26x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x26x26x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x26x26x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x26x26x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x26x26x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x26x26x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x26x26x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x26x26x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x26x26x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x26x26x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x26x26x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x26x26x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x26x26x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x26x26x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x26x26x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x26x26x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x26x26x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x26x26x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x26x26x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x26x26x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x26x26x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x26x26x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x26x26x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x26x26x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x26x26x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x26x26x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x26x26x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x270x39x1x3x3x1x1x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x270x39x1x3x3x1x1x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x270x39x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x270x39x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x271x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x271x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x271x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x271x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x271x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x271x199x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x271x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x271x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x271x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x271x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x271x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x271x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x271x39x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x271x39x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x271x39x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x271x39x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x272x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x272x160x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x272x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x272x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x272x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x272x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x272x176x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x176x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x272x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x272x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x272x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x272x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x272x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x272x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x272x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x272x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x272x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x272x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x272x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x272x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x272x200x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x272x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x272x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x272x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x272x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x272x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x272x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x272x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x272x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x273x39x1x3x3x1x1x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x273x39x1x3x3x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x274x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x274x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x274x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x274x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x274x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x274x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x274x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x274x19x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x274x39x1x3x3x1x1x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x274x39x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x276x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x276x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x276x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x276x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x277x39x1x3x3x1x1x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x277x39x1x3x3x1x1x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x277x39x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x277x39x1x3x3x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x279x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x279x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x279x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x279x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x279x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x279x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x279x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x279x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x279x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x279x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x279x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x279x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x279x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x279x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x279x39x1x3x3x1x1x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x279x39x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x27x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x27x20x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x20x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x27x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x27x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x27x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x27x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x27x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x27x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,7;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x32x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x27x27x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x27x27x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x27x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x27x27x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x27x27x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x27x27x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x27x27x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x27x27x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x27x27x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[8];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x256x27x27x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x27x27x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x27x27x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x27x27x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x27x27x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x27x27x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x27x27x1x5x5x1x96x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x27x27x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x280x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x280x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x280x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x280x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x280x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x280x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x280x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x280x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x280x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x280x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x280x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x280x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x280x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x280x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x280x39x1x3x3x1x1x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x280x39x1x3x3x1x1x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x280x39x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x280x39x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x282x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x282x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x282x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x282x19x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x284x39x1x3x3x1x1x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x284x39x1x3x3x1x1x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x284x39x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x284x39x1x3x3x1x256x73x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x285x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x285x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x285x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x285x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x286x39x1x3x3x1x1x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x286x39x1x3x3x1x1x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x286x39x1x3x3x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x287x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x287x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x287x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x287x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x287x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x287x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x287x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x287x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x287x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x287x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x287x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x287x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x287x39x1x3x3x1x1x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x287x39x1x3x3x1x1x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x287x39x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x287x39x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x288x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x288x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x288x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x288x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x288x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x256x288x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x288x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x288x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x288x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x288x184x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x288x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x288x184x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x288x192x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x288x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x288x192x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x288x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x288x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x288x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x288x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x288x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x2896x2896x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2897x2897x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x2897x2897x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x289x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x289x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x289x39x1x3x3x1x1x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x289x39x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x19x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x19x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x19x1x1x1x1x128x1x0x0x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x28x19x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x19x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x28x19x1x3x3x1x128x1x1x1x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x28x19x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x19x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x19x1x5x5x1x128x1x2x2x0x2x3x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x28x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x28x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x28x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x28x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x28x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x28x25x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x25x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x28x28x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x256x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x21x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x21x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, OddC, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:129
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:133;TransposedConvBinWinoRxS<3-2>:146
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:252
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:147;TransposedConvBinWinoRxS<3-2>:160
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:254
2x256x28x28x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:133;TransposedConvBinWinoRxS<3-2>:153
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:212
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:201
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:140;TransposedConvBinWinoRxS<3-2>:143
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:236
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:255
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[5];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:129
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:248
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:230
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:132;TransposedConvBinWinoRxS<3-2>:129
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:138
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:252
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:132;TransposedConvBinWinoRxS<3-2>:133
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:253
2x256x28x28x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:129
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:251
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;TransposedConvBinWinoRxS<3-2>:255
2x256x28x28x1x1x1x1x512x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:253
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:130
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;TransposedConvBinWinoRxS<3-2>:256
2x256x28x28x1x1x1x1x512x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:132
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:128
2x256x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:138
2x256x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:237
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:133;TransposedConvBinWinoRxS<3-2>:184
2x256x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:148
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x515x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x515x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,97[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x1x1x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x1x1x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x28x28x1x1x1x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x28x28x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x1x1x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x28x28x1x1x1x1x728x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x728x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x175x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x188x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x191x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x197x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x198x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x202x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x205x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x207x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x212x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x220x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x222x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x226x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x234x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x236x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x237x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x244x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x245x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x246x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x249x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x254x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x1x1x80x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x1x1x1x80x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x80x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x81x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x81x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x5x1x256x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195
2x256x28x28x1x2x2x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x101x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x102x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x103x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x104x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x106x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x107x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x108x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x109x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x113x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x115x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x117x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x121x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x123x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x124x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x125x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x126x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x127x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x130x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x131x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x132x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x133x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x134x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x135x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x136x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x138x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x139x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x140x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x141x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x142x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x144x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x146x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x147x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x148x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x149x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x151x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x152x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x153x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x154x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x156x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x159x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x160x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x161x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x162x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x164x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x165x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x166x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x167x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x168x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x169x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x173x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x174x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x176x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x178x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x180x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x184x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x185x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x186x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x188x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x191x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x192x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x194x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x195x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x196x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x197x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x202x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x207x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x210x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x211x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x212x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x213x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x214x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x215x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x216x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x219x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x220x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x221x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x225x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x227x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x228x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x229x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x231x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x232x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x233x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x234x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x236x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x238x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x240x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x243x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x244x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x245x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x247x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x248x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x249x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x250x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x254x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x255x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x2x2x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x2x2x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x72x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x78x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x79x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x2x2x1x256x80x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x81x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x82x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x87x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x88x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x89x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x256x90x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x91x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x92x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x93x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x95x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x2x2x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x2x2x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x2x2x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x128x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x16x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x16x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x1x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x1x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x1x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x1x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x1x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x28x28x1x3x3x1x2048x1x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x256x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x256x28x28x1x3x3x1x2048x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x256x28x28x1x3x3x1x2048x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x2048x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x2x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x256x28x28x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x28x28x1x3x3x1x2048x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x28x28x1x3x3x1x2048x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x32x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x28x28x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x28x28x1x3x3x1x2048x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x2048x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x28x28x1x3x3x1x2048x4x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x28x28x1x3x3x1x2048x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x4x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x28x28x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x28x28x1x3x3x1x2048x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x2048x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x28x28x1x3x3x1x2048x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x2048x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x512x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x28x28x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x256x28x28x1x3x3x1x2048x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x2048x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x28x28x1x3x3x1x2048x64x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x256x28x28x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x256x28x28x1x3x3x1x2048x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x2048x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x2048x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x28x28x1x3x3x1x2048x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x2048x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x3x1x2048x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x28x28x1x3x3x1x2048x8x36x36x0x1x1x0x36x36x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x28x28x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+8
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x256x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x28x28x1x3x3x1x256x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x28x28x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x5x1x256x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5]
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x3x7x1x256x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x5x1x1x256x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x28x28x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x5x5x1x256x4x2x2x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:197
2x256x28x28x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x28x28x1x7x7x1x256x8x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x28x28x1x7x7x1x512x4x3x3x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x256x28x56x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x28x56x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x28x56x1x1x1x1x128x1x0x0x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x28x56x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x56x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x28x56x1x3x3x1x128x1x1x1x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x28x56x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x56x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x28x56x1x5x5x1x128x1x2x2x0x2x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x290x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x290x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x290x39x1x3x3x1x1x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x290x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x290x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x290x39x1x3x3x1x256x71x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x291x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x291x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x291x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x291x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x293x39x1x3x3x1x1x67x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x293x39x1x3x3x1x256x67x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x295x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x295x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x295x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x295x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x295x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x295x39x1x3x3x1x1x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x295x39x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x296x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x296x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x296x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x296x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x296x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x296x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x296x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x296x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x296x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x296x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x296x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x296x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x296x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x296x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x296x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x296x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x296x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x296x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x296x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x296x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x296x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x296x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x296x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x296x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x296x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x296x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x297x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x297x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x297x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x297x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x298x39x1x3x3x1x1x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x298x39x1x3x3x1x1x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x298x39x1x3x3x1x1x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x298x39x1x3x3x1x256x66x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x298x39x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x298x39x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x29x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x29x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x29x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x29x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x29x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x29x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x29x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x29x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x29x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x29x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x29x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x29x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x29x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x29x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x29x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x29x29x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x29x29x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:232
2x256x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:211
2x256x29x29x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:201
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:116
2x256x29x29x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:109
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:222
2x256x29x29x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:237
2x256x29x29x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:233
2x256x29x29x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:237
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x29x29x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:246
2x256x29x29x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:233
2x256x29x29x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:212
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:251
2x256x29x29x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:249
2x256x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x29x29x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:244
2x256x29x29x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:201
2x256x29x29x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:226
2x256x29x29x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:70
2x256x29x29x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:58
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x2x2x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x303x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x303x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x303x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x303x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x303x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x303x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x303x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x303x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x303x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x303x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x304x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x304x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x304x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x304x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x304x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x304x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x304x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x304x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x304x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x304x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x304x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x304x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x304x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x304x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x304x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x304x192x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x304x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x304x192x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x304x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x304x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x304x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x304x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x304x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x304x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x304x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x304x200x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x304x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x304x200x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x304x39x1x3x3x1x1x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x304x39x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x305x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x305x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x305x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x305x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x305x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x305x19x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x305x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x305x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x305x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x305x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x306x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x306x39x1x3x3x1x1x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x306x39x1x3x3x1x1x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x306x39x1x3x3x1x1x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x306x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x306x39x1x3x3x1x256x61x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x306x39x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x306x39x1x3x3x1x256x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x307x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x307x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x307x39x1x3x3x1x1x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x307x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x307x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x307x39x1x3x3x1x256x65x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x308x39x1x3x3x1x1x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x308x39x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x309x39x1x3x3x1x1x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x309x39x1x3x3x1x1x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x309x39x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x309x39x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x30x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x30x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x30x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x30x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x30x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x30x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x30x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x30x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x30x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x30x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x30x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x30x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x30x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x30x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x30x22x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x30x22x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x30x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x30x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x30x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x30x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x30x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x30x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x30x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x30x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x30x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x30x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x30x30x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x30x30x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x30x30x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x256x30x30x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x1x0x0x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x30x30x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x30x30x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x30x30x1x3x3x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x30x30x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x30x30x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x30x30x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x30x30x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x30x30x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x310x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x310x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x310x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x310x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x311x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x311x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x311x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x311x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x311x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x311x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x311x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x311x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x311x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x311x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x311x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x311x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x311x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x311x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x311x39x1x3x3x1x1x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x311x39x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x312x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x312x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x312x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x312x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x312x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x312x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x312x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x312x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x312x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x312x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x312x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x312x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x312x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x312x39x1x3x3x1x1x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x312x39x1x3x3x1x1x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x312x39x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x312x39x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x313x39x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x313x39x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x313x39x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x313x39x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x314x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x314x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x314x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x314x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x314x39x1x3x3x1x1x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x314x39x1x3x3x1x256x70x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x315x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x315x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x315x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x315x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x316x39x1x3x3x1x1x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x316x39x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x319x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x319x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x319x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x319x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x319x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x319x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x319x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x319x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x319x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x319x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x31x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x31x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x31x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x31x20x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x20x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x31x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x31x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x31x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x31x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x31x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x31x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x31x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x31x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x31x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x31x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x31x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x31x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x31x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x31x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x31x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x31x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x31x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x31x23x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x23x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x31x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x31x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x31x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x31x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x31x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x31x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x31x24x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x24x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x31x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x31x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x31x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x31x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x31x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x31x1x3x3x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x31x31x1x3x3x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x31x31x1x3x3x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x31x31x1x3x3x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x31x31x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x31x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x31x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x31x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x31x31x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x31x31x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x256x320x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x320x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x320x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x320x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x320x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x320x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x320x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x320x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x320x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x320x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x320x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x320x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x320x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x320x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x320x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x320x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x320x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x320x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x320x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x320x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x320x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x320x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x320x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x320x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x320x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x320x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x320x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x320x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x320x200x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x320x39x1x3x3x1x1x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x320x39x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x321x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x321x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x321x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x321x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x321x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x321x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x321x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x321x19x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x321x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x321x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x321x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x321x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x322x39x1x3x3x1x1x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x322x39x1x3x3x1x1x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x322x39x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x322x39x1x3x3x1x256x68x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x323x39x1x3x3x1x1x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x323x39x1x3x3x1x1x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x323x39x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x323x39x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x324x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x324x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x324x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x324x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x325x39x1x3x3x1x1x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x325x39x1x3x3x1x1x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x325x39x1x3x3x1x1x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x325x39x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x325x39x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x325x39x1x3x3x1x256x57x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x327x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x327x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x327x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x327x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x327x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x327x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x327x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x327x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x327x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x327x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x327x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x327x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x327x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x327x19x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x327x39x1x3x3x1x1x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x327x39x1x3x3x1x1x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x327x39x1x3x3x1x1x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x327x39x1x3x3x1x1x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x327x39x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x327x39x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x327x39x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x327x39x1x3x3x1x256x63x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x328x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x328x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x328x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x328x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x328x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x328x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x328x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x328x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x328x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x328x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x328x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x329x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x329x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x329x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x329x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x32x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x32x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x32x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x32x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x32x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x32x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x32x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x32x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x32x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x32x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x32x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x32x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x32x23x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x23x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x32x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x32x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x32x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x32x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x32x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x32x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x32x32x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x32x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x32x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[4];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:171
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x32x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x256x32x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x32x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x32x32x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x256x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x2x2x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x2x2x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x32x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x32x32x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x32x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x32x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x32x32x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x32x32x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x32x32x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x32x32x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x32x32x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x32x32x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x32x32x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x32x32x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x32x32x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x32x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x32x32x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x32x32x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x32x32x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x32x32x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x32x32x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x32x32x1x4x4x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x4x4x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x32x32x1x4x4x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x32x32x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x32x32x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x32x32x1x5x5x1x256x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x32x32x1x7x7x1x256x16x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x32x32x1x7x7x1x256x2x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x32x32x1x7x7x1x256x8x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x330x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x330x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x330x39x1x3x3x1x1x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x330x39x1x3x3x1x1x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x330x39x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x330x39x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x331x39x1x3x3x1x1x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x331x39x1x3x3x1x1x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x331x39x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x331x39x1x3x3x1x256x53x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x332x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x332x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x332x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x332x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x333x39x1x3x3x1x1x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x333x39x1x3x3x1x1x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x333x39x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x333x39x1x3x3x1x256x62x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x335x159x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x335x159x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x335x167x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x335x167x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x335x175x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x335x175x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x335x183x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x335x183x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x335x191x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x335x191x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x335x199x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x335x199x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x335x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x335x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x335x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x335x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x336x160x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x336x160x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x336x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x336x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x336x168x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x336x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x336x168x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x336x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x336x176x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x176x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x336x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x336x176x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x336x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x336x176x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x336x184x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x184x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x336x184x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x336x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x336x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x336x184x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x336x192x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x336x192x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x336x192x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x336x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x336x192x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x336x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x336x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x336x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x336x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x336x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x336x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x336x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x336x19x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x336x200x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x336x200x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x336x200x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x336x39x1x3x3x1x1x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x336x39x1x3x3x1x1x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x336x39x1x3x3x1x1x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x336x39x1x3x3x1x1x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x336x39x1x3x3x1x256x52x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x336x39x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x336x39x1x3x3x1x256x54x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x336x39x1x3x3x1x256x60x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x337x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x337x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x337x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x337x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x337x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x337x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x337x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x337x19x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x33x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x33x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x33x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x33x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x33x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x33x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x33x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x33x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x33x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x33x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x33x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x33x22x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x22x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x33x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x33x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x33x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x33x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x33x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x33x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x33x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x33x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x33x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x33x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x33x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x33x33x1x3x3x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x33x1x3x3x1x224x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x33x33x1x3x3x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x33x33x1x3x3x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x33x33x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x33x33x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x33x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x33x33x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x33x33x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x33x33x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x33x33x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x342x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x342x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x342x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x342x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x344x39x1x3x3x1x1x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x344x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x344x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x344x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x344x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x344x39x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x344x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x344x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x344x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x344x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x346x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x346x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x349x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x349x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x349x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x349x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x349x39x1x3x3x1x1x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x349x39x1x3x3x1x1x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x349x39x1x3x3x1x1x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x349x39x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x349x39x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x349x39x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x34x19x1x3x3x1x256x329x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x34x19x1x3x3x1x256x329x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x34x20x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x34x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x34x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x34x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x34x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x34x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x34x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x34x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x34x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x34x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x34x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x34x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x34x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x34x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x34x22x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x34x22x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x34x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x34x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x34x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x34x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x34x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x34x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x34x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x34x25x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x25x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x34x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x34x34x1x4x4x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x34x34x1x4x4x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x34x34x1x4x4x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x34x34x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x256x34x34x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x256x34x34x1x7x7x1x256x1x6x6x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x256x350x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x350x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x350x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x350x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x352x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x352x39x1x3x3x1x1x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x352x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x352x39x1x3x3x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x353x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x353x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x353x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x353x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x356x39x1x3x3x1x1x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x356x39x1x3x3x1x1x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x356x39x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x356x39x1x3x3x1x256x46x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x357x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x357x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x357x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x357x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x357x39x1x3x3x1x1x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x357x39x1x3x3x1x1x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x357x39x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x357x39x1x3x3x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x358x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x358x39x1x3x3x1x1x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x358x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x358x39x1x3x3x1x256x49x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x35x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x35x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x35x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x35x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x35x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x35x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x35x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x35x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x35x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x35x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x35x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x35x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x35x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x48x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x35x35x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x35x35x1x3x3x1x224x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x35x35x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x35x35x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x35x35x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x35x35x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x360x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x360x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x360x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x360x19x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x361x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x361x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x361x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x361x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x361x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x361x19x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x362x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x362x39x1x3x3x1x1x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x362x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x362x39x1x3x3x1x256x55x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x363x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x363x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x3648x4576x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x3648x4576x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x365x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x365x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x365x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x365x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x366x39x1x3x3x1x1x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x366x39x1x3x3x1x1x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x366x39x1x3x3x1x1x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x366x39x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x366x39x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x366x39x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x368x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x368x19x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x36x171x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x36x171x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[5];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x36x171x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x36x171x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x36x171x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x171x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x36x171x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x256x36x171x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x36x171x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x36x171x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x36x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x36x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x36x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x36x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x36x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x36x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x36x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x36x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x36x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x36x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x36x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x36x23x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x23x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x36x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x36x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x36x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x36x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x36x24x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x24x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x36x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,32,32,32,2,1,1,2,1,0,0,3,0,0,1,4,8,1,1,8,1,16,1,4,2,1,1,8,1,16,38[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x36x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x36x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x36x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x36x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x36x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x36x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x36x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x36x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x372x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x372x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x374x39x1x3x3x1x1x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x374x39x1x3x3x1x1x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x374x39x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x374x39x1x3x3x1x256x47x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x375x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x375x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x376x39x1x3x3x1x1x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x376x39x1x3x3x1x1x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x376x39x1x3x3x1x256x40x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x376x39x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x377x39x1x3x3x1x1x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x377x39x1x3x3x1x1x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x377x39x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x377x39x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x378x39x1x3x3x1x1x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x378x39x1x3x3x1x1x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x378x39x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x378x39x1x3x3x1x256x41x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x379x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x379x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x379x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x379x19x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x37x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x37x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x37x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x37x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x37x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x37x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x37x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x37x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x37x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x37x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x37x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x37x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x37x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x37x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x37x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x37x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x37x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x37x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x37x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x37x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x37x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x37x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x37x37x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x37x37x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x37x37x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x37x37x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x37x37x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x37x37x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x37x37x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x37x37x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x380x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x380x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x380x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x380x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x381x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x381x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x382x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x382x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x382x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x382x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x383x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x383x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x384x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x384x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x384x384x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x388x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x388x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x388x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x388x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x388x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x388x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x388x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x388x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x389x39x1x3x3x1x1x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x389x39x1x3x3x1x1x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x389x39x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x389x39x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x256x38x173x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x38x173x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x256x38x173x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x173x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x173x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x173x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x173x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x173x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x38x173x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x256x38x173x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x173x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x173x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x38x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x38x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x38x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x38x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x38x24x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x24x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x38x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x38x25x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x25x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:243
2x256x38x38x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:34
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:243
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:52
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:246
2x256x38x38x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:58;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:63;TransposedConvBinWinoRxS<3-2>:45
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x38x38x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:52;TransposedConvBinWinoRxS<3-2>:35
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:67
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:63;TransposedConvBinWinoRxS<3-2>:34
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];TransposedConvBinWinoRxS<3-2>:68
2x256x38x38x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x256x38x38x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:34
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:246
2x256x38x38x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:84;TransposedConvBinWinoRxS<3-2>:41
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:239
2x256x38x38x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:240
2x256x38x38x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:66
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:65
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:88
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:75
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:75;TransposedConvBinWinoRxS<3-2>:66
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:105;TransposedConvBinWinoRxS<3-2>:84
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:90
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:91
2x256x38x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:69
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:248
2x256x38x38x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:67
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:152
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:80
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;TransposedConvBinWinoRxS<3-2>:143
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:180
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:239
2x256x38x38x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:70;TransposedConvBinWinoRxS<3-2>:72
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:238
2x256x38x38x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:240
2x256x38x38x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:167;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:246
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:145;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];TransposedConvBinWinoRxS<3-2>:242
2x256x38x38x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:36
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:157;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x38x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:131;TransposedConvBinWinoRxS<3-2>:34
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:250
2x256x38x38x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:138;TransposedConvBinWinoRxS<3-2>:42
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:45
2x256x38x38x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:133;TransposedConvBinWinoRxS<3-2>:42
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:228
2x256x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:136;TransposedConvBinWinoRxS<3-2>:35
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:77
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:137;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x128x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];TransposedConvBinWinoRxS<2-3>:150;TransposedConvBinWinoRxS<3-2>:33
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:91
2x256x38x38x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:163;TransposedConvBinWinoRxS<3-2>:56
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];TransposedConvBinWinoRxS<2-3>:138;TransposedConvBinWinoRxS<3-2>:40
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:237
2x256x38x38x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:144;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x38x38x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:239
2x256x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:158;TransposedConvBinWinoRxS<3-2>:32
2x256x38x38x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:252
2x256x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:65
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:128
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:65
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:249
2x256x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:70
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:254
2x256x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:252
2x256x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:72
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:90
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:97
2x256x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:69
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:231
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:227
2x256x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:132
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:75
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:136
2x256x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:210
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:202
2x256x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:74
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x256x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:237
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:247
2x256x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:65
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:252
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:64
2x256x38x38x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:248
2x256x38x38x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:248
2x256x38x38x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:235
2x256x38x38x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:253
2x256x38x38x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:123
2x256x38x38x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:241
2x256x38x38x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:249
2x256x38x38x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:255
2x256x38x38x1x3x3x1x512x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:247
2x256x38x38x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x256x38x38x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:70
2x256x38x38x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:211
2x256x38x38x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x512x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x38x38x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:126
2x256x38x38x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:251
2x256x38x38x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x38x38x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x256x38x38x1x3x3x1x512x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x38x38x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x38x38x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x38x38x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x38x38x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:224
2x256x38x38x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x392x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x392x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x392x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x392x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x392x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x392x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x395x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x395x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x395x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x395x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x39x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x39x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x39x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x39x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x39x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x39x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x39x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x39x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x39x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x39x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x39x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x39x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x39x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x39x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x39x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x39x39x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x39x39x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x39x39x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x39x39x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x3x3x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:21
2x256x3x3x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:33
2x256x3x3x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:19
2x256x3x3x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:52
2x256x3x3x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:4
2x256x3x3x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:4
2x256x3x3x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:12
2x256x3x3x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x3x3x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:74
2x256x3x3x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x3x3x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:39
2x256x3x3x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:32
2x256x3x3x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:68
2x256x3x3x1x3x3x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:130;TransposedConvBinWinoRxS<3-2>:36
2x256x3x3x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:60
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:134;TransposedConvBinWinoRxS<3-2>:38
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];TransposedConvBinWinoRxS<3-2>:64
2x256x3x3x1x3x3x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];TransposedConvBinWinoRxS<2-3>:150;TransposedConvBinWinoRxS<3-2>:38
2x256x3x3x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:89
2x256x3x3x1x3x3x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:151;TransposedConvBinWinoRxS<3-2>:36
2x256x3x3x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:81
2x256x3x3x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:142;TransposedConvBinWinoRxS<3-2>:35
2x256x3x3x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];TransposedConvBinWinoRxS<3-2>:15
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:170;TransposedConvBinWinoRxS<3-2>:101
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];TransposedConvBinWinoRxS<3-2>:12
2x256x3x3x1x3x3x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;TransposedConvBinWinoRxS<2-3>:133;TransposedConvBinWinoRxS<3-2>:40
2x256x3x3x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:128
2x256x3x3x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:144;TransposedConvBinWinoRxS<3-2>:44
2x256x3x3x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[6];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];TransposedConvBinWinoRxS<3-2>:12
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];TransposedConvBinWinoRxS<2-3>:158;TransposedConvBinWinoRxS<3-2>:110
2x256x3x3x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x256x3x3x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];TransposedConvBinWinoRxS<3-2>:26
2x256x3x3x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:38
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];TransposedConvBinWinoRxS<3-2>:17
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];TransposedConvBinWinoRxS<2-3>:148;TransposedConvBinWinoRxS<3-2>:74
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];TransposedConvBinWinoRxS<3-2>:6
2x256x3x3x1x3x3x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:40
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];TransposedConvBinWinoRxS<3-2>:10
2x256x3x3x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];TransposedConvBinWinoRxS<2-3>:243;TransposedConvBinWinoRxS<3-2>:34
2x256x3x3x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:256
2x256x3x3x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:164;TransposedConvBinWinoRxS<3-2>:69
2x256x3x3x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x3x3x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];TransposedConvBinWinoRxS<3-2>:32
2x256x3x3x1x3x3x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:128;TransposedConvBinWinoRxS<3-2>:45
2x256x3x3x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:32
2x256x3x3x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:129;TransposedConvBinWinoRxS<3-2>:38
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x3x3x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x3x3x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x256x1x0x0x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x256x3x3x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x324x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:52
2x256x3x3x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:55
2x256x3x3x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:55
2x256x3x3x1x3x3x1x340x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:46
2x256x3x3x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:24
2x256x3x3x1x3x3x1x340x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:105
2x256x3x3x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x3x3x1x3x3x1x340x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:34
2x256x3x3x1x3x3x1x340x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:14
2x256x3x3x1x3x3x1x340x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:14
2x256x3x3x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:177
2x256x3x3x1x3x3x1x340x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x3x3x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:54
2x256x3x3x1x3x3x1x340x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:28
2x256x3x3x1x3x3x1x340x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x344x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x3x3x1x3x3x1x344x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x3x3x1x3x3x1x344x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x400x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x400x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x400x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x400x39x1x3x3x1x1x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x400x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x400x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x400x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x400x39x1x3x3x1x256x45x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x401x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x401x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x401x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x401x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x401x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x401x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x403x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x403x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x403x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x403x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x404x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x404x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x404x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x404x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x405x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x405x39x1x3x3x1x1x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x405x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x405x39x1x3x3x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x406x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x406x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x408x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x408x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x408x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x408x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x408x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x408x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x4095x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x4096x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x4096x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x4097x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x4097x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x40x175x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x40x175x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x40x175x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x40x175x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x40x175x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x40x175x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x40x175x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x40x175x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x40x175x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x40x175x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x40x175x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x40x175x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x40x175x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x40x175x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x40x175x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x256x40x175x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x40x19x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x40x19x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x40x19x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x40x19x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x40x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x40x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x40x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x40x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x40x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x40x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x40x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x40x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x40x1x1x3x1x512x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x40x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x40x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x40x40x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x40x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x40x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x52x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x52x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x40x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x54x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x40x54x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x54x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x40x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x54x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x54x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x40x54x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x40x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x54x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x54x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x54x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x54x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x56x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x40x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x40x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x40x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x40x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x40x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x60x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x60x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x40x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x40x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x62x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x62x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x40x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x40x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x40x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x62x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x62x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x62x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x64x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x64x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x66x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x66x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x40x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x66x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x40x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x68x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x68x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x40x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x40x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x40x70x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x40x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x40x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x40x72x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x72x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x40x72x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x76x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x76x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x40x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x40x78x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x78x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x40x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x40x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x40x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x82x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x40x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x82x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x40x82x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x40x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x40x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x40x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x40x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x40x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x40x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x40x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x40x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x40x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x410x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x410x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x410x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x410x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x411x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x411x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x411x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x411x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x412x39x1x3x3x1x1x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x412x39x1x3x3x1x1x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x412x39x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x412x39x1x3x3x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x415x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x415x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x415x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x415x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x416x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x416x19x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x417x39x1x3x3x1x1x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x417x39x1x3x3x1x1x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x417x39x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x417x39x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x418x39x1x3x3x1x1x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x418x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x418x39x1x3x3x1x1x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x418x39x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x418x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x418x39x1x3x3x1x256x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x419x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x419x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x41x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x41x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x41x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x41x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x41x20x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x41x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x41x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x22x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x41x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x41x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x41x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x41x23x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x23x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x41x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x41x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x41x24x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x24x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x41x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x41x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x41x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x41x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x421x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x421x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x421x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x421x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x422x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x422x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x422x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x422x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x423x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x423x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x423x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x423x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x427x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x427x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x427x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x427x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x427x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x427x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x428x39x1x3x3x1x1x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x428x39x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x42x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x42x20x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x20x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x21x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x42x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x42x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x42x21x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x42x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x22x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x22x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x22x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x23x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x42x24x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x24x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x42x25x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x25x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x25x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x25x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x42x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x42x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x42x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x42x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x52x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x52x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x52x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x52x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x52x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x52x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x42x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x52x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x52x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x42x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x54x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x54x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x42x54x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x54x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x42x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x56x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x56x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x56x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x42x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x58x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x58x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x58x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x58x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x42x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x42x60x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x42x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x62x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x62x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x62x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x64x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x42x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x64x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x64x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x42x64x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x64x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x66x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x42x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x70x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x70x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x42x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x70x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x42x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x72x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x72x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x74x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x74x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x42x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x74x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x76x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x76x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x42x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x76x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x76x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x42x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x42x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x42x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x42x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x42x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x42x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x42x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x42x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x42x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x42x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x42x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x42x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x431x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x431x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x431x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x431x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x436x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x436x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x436x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x436x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x436x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x436x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x438x39x1x3x3x1x1x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x438x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x438x39x1x3x3x1x1x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x438x39x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x438x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x438x39x1x3x3x1x256x39x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x441x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x441x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x441x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x441x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x442x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x442x39x1x3x3x1x1x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x442x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x442x39x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x444x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x444x39x1x3x3x1x1x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x444x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x444x39x1x3x3x1x256x38x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x446x39x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x446x39x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x446x39x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x446x39x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x447x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x447x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x447x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x447x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x44x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x44x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x44x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x44x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x44x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x44x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x44x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x44x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x54x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x54x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x44x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x56x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x44x56x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x58x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x44x58x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x58x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x44x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x60x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x44x60x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x60x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x60x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x62x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x44x62x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x44x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x44x62x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x62x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x44x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x64x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x66x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x66x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x66x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x66x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x66x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x44x66x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x44x66x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x66x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x44x66x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x44x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x68x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x68x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x44x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x70x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x44x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x70x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x44x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x44x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x44x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x44x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x44x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x44x72x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x74x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x74x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x44x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x44x74x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x74x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x44x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x76x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x44x76x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x44x76x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x76x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x44x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x78x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x44x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x44x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x44x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x44x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x82x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x44x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x44x82x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x44x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x44x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x44x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x44x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x44x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x44x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x44x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x44x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x44x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x44x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x450x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x450x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x450x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x450x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x452x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x452x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x452x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x452x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x453x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x453x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x453x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x453x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x453x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x453x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x453x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x453x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x454x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x454x19x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x455x39x1x3x3x1x1x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x455x39x1x3x3x1x256x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x4576x3648x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x4576x3648x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x458x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x458x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x458x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x458x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x45x19x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x45x19x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x45x19x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x45x19x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x462x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x462x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x462x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x462x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x462x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x462x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x462x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x462x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x463x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x463x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x465x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x465x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x465x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x465x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x467x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x467x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x467x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x467x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x468x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x468x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x468x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x468x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x46x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x46x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x46x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x46x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x46x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x46x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x46x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x46x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x46x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x54x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x56x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x46x56x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x58x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x58x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x46x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x46x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x60x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x62x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x62x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x62x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x46x62x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x62x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x62x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x64x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x64x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x64x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x66x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x46x66x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x66x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x68x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x68x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x46x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x70x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x46x70x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x70x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x46x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x70x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x70x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x46x70x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x70x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x70x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x70x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x46x72x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x72x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x46x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x46x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x74x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x74x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x46x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x74x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x74x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x74x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x76x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x76x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x76x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x78x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x46x78x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x46x78x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x46x78x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x46x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x46x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x46x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x46x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x46x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x46x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x46x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x46x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x46x82x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x46x82x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x46x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x46x82x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x82x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x82x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x82x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x46x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x46x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x46x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x46x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x46x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x46x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x46x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x46x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x46x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x46x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x470x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x470x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x470x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x470x39x1x3x3x1x1x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x470x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x470x39x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x471x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x471x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x471x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x471x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x472x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x472x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x472x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x472x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x472x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x472x19x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x476x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x476x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x476x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x476x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x478x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x478x39x1x3x3x1x1x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x478x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x478x39x1x3x3x1x256x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x479x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x479x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x479x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x479x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x480x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x480x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x480x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x480x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x483x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x483x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x483x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x483x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x484x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x484x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x484x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x484x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x485x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x485x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x486x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x486x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x486x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x486x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x487x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x487x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x48x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x48x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x48x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x48x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x48x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x48x1x2x2x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x48x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x48x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x52x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x52x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x52x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x52x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x52x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x52x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x52x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x52x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x54x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x54x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x48x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x54x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x48x56x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x48x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x56x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x56x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x48x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x58x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x48x58x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x58x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x48x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x58x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x58x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x58x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x60x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x62x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x48x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x62x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x64x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x64x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x64x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x64x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x64x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x66x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x66x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x48x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x48x66x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x68x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x68x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x48x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x68x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x70x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x48x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x48x70x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x72x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x48x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x72x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x72x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x72x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x72x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x72x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x74x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x48x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x74x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x48x74x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x74x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x74x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x74x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x74x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x76x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x76x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x48x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x48x76x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x76x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x78x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x78x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x78x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x48x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x78x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x78x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x78x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x78x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x48x78x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x78x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x78x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x78x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x78x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x80x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x80x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x80x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x48x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x80x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x80x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x80x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x80x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x48x82x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x82x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x48x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x48x82x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x84x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x48x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x48x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x48x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x48x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x84x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x48x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x48x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x48x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x48x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x48x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x490x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x490x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x491x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x491x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x493x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x493x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x493x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x493x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x493x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x493x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x494x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x494x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x496x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x496x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x496x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x496x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x496x496x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x496x528x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x497x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x497x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x498x39x1x3x3x1x1x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x498x39x1x3x3x1x1x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x498x39x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x498x39x1x3x3x1x256x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x4x1024x1x1x1x1x513x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x1024x1x1x1x1x513x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x16384x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x4x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x4x16x1x1x1x1x513x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x256x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x4x256x1x1x1x1x513x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x256x1x1x1x1x513x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x4096x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x4x4096x1x1x1x1x513x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x4x4x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x4x4x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x4x4x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x4x4x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x4x4x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x3x3x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x4x4x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x4x4x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x4x4x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x4x4x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x4x4x1x3x3x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x4x4x1x3x3x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x4x4x1x3x3x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x4x4x1x3x3x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x4x4x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x4x4x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x4x4x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x4x4x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x4x4x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x4x4x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x4x4x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x4x4x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x4x4x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x4x4x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x4x4x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x4x4x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x4x4x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x4x4x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x4x4x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x4x4x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x4x4x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x4x4x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x256x4x4x1x3x3x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x3x3x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x4x4x1x3x3x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x4x4x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x4x4x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x4x4x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x4x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x4x4x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x4x4x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x4x4x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x4x8x1x3x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x4x8x1x3x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x500x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x500x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x501x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x501x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x501x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x501x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x504x39x1x3x3x1x1x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x504x39x1x3x3x1x1x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x504x39x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x504x39x1x3x3x1x256x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x508x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x508x39x1x3x3x1x1x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x508x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x508x39x1x3x3x1x1x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x508x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x508x39x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x508x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x508x39x1x3x3x1x256x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x509x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x509x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x509x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x509x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x50x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x50x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x50x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x50x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x50x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x50x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x54x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x54x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x50x54x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x54x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x56x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x56x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x50x56x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x50x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x50x56x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x58x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x58x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x50x58x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x58x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x60x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x60x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x60x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x50x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x60x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x62x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x62x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x62x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x50x62x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x50x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x64x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x64x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x66x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x66x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x66x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x68x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x68x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x68x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x50x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x68x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x68x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x50x68x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x68x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x68x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x68x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x68x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x68x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x70x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x70x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x50x70x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x70x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x70x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x70x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x50x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x72x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x72x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x50x72x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x72x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x72x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x72x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x74x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x74x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x50x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x74x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x74x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x76x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x76x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x76x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x50x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x76x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x76x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x76x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x76x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x76x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x76x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x50x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x50x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x76x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x76x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x78x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x78x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x78x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x50x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x50x80x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x50x80x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x80x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x50x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x80x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x50x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x82x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x50x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x82x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x82x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x50x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x82x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x82x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x50x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x50x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x50x82x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x82x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x50x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x50x84x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x50x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x50x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x50x84x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x50x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x256x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:250
2x256x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x256x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246
2x256x512x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x512x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x512x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x128x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x512x512x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x512x512x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x18x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x18x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:244
2x256x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x512x512x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252
2x256x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x256x4x2x2x0x2x2x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x512x512x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x512x512x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x512x512x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x512x512x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x512x512x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x512x512x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x515x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x515x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x515x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x515x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x51x51x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x51x51x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x51x51x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x51x51x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x51x51x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x51x51x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x522x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x522x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x522x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x522x39x1x3x3x1x1x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x522x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x522x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x522x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x522x39x1x3x3x1x256x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x525x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x525x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x525x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x525x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x526x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x526x19x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x528x496x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x528x528x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x529x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x529x39x1x3x3x1x1x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x529x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x529x39x1x3x3x1x256x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x52x19x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x52x19x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x52x19x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x52x19x1x3x3x1x256x440x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x52x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x52x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x52x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x52x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x52x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x52x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x52x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x52x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x52x40x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x40x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x52x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x52x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x52x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x52x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x52x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x52x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x52x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x52x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x52x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x52x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x52x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x52x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x52x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x52x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x52x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x52x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x52x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x52x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x52x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x52x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x52x52x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x52x52x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x52x52x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x52x52x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x52x52x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x52x52x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x52x52x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x52x52x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x52x52x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x52x52x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x531x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x531x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x531x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x531x19x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x536x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x536x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x536x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x536x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x537x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x537x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x537x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x537x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x53x53x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x53x53x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x53x53x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x53x53x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x53x53x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x53x53x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x53x53x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x540x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x540x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x540x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x540x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x544x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x544x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x544x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x544x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x546x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x546x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x546x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x546x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x549x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x549x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x549x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x549x39x1x3x3x1x1x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x549x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x549x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x549x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x549x39x1x3x3x1x256x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x54x19x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x54x19x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x54x19x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x54x19x1x3x3x1x256x397x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x54x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x54x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x54x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x54x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x54x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x54x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x54x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x54x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x54x40x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x40x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x54x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x54x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x54x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x54x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x54x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x54x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x54x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x54x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x54x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x54x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x54x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x54x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x54x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x54x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x54x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x54x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x54x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x54x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x54x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x54x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x54x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x553x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x553x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x553x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x553x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x55x55x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x55x55x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x55x55x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x560x39x1x3x3x1x1x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x560x39x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x566x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x566x39x1x3x3x1x1x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x566x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x566x39x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x568x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x568x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x568x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x568x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x19x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x19x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x19x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x19x1x3x3x1x256x313x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x56x28x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x56x28x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x56x28x1x1x1x1x128x1x0x0x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x28x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x56x28x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x28x1x3x3x1x128x1x1x1x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x56x28x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x28x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x28x1x5x5x1x128x1x2x2x0x1x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x56x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x56x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x56x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x56x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x56x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x56x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x56x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x56x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x50x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x50x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:240
2x256x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x256x56x56x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:250
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x56x56x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:252
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x256x56x56x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:252
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x256x56x56x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:239
2x256x56x56x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x56x56x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:208
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:190
2x256x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8
2x256x56x56x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x256x56x56x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x256x56x56x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:202
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:212
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:255
2x256x56x56x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x256x56x56x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x256x56x56x1x1x1x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:240
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:230
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x56x56x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:255
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[1]
2x256x56x56x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x256x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:207
2x256x56x56x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x1x1x1x512x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x516x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x517x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x56x56x1x1x1x1x517x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x256x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[5];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:18
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:242
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:17
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];TransposedConvBinWinoRxS<2-3>:30;TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:171
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:30;TransposedConvBinWinoRxS<3-2>:20
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:191
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:17
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:193
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:181
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:46;TransposedConvBinWinoRxS<3-2>:22
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:20
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];TransposedConvBinWinoRxS<2-3>:47;TransposedConvBinWinoRxS<3-2>:60
2x256x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:29;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:30;TransposedConvBinWinoRxS<3-2>:64
2x256x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];TransposedConvBinWinoRxS<2-3>:30;TransposedConvBinWinoRxS<3-2>:58
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:244
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:27;TransposedConvBinWinoRxS<3-2>:33
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:44
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:243
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:25
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:18
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:204
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:17
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:210
2x256x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:19
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:256
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:22
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;TransposedConvBinWinoRxS<3-2>:225
2x256x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:46
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+128
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:253
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,194
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x256x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:47
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:234
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:232
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:18
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:254
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:253
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x256x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:24
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:245
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:17
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];TransposedConvBinWinoRxS<2-3>:24;TransposedConvBinWinoRxS<3-2>:20
2x256x56x56x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:195
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:208
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:50;TransposedConvBinWinoRxS<3-2>:19
2x256x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,193[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x56x56x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x56x56x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x56x56x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x56x56x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x2x2x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x56x56x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x56x56x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x2x2x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x56x56x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x2x2x1x256x800x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x256x56x56x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x2x2x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:32
2x256x56x56x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7]
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x1x1x1x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x56x56x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64
2x256x56x56x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x56x56x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x56x56x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+-1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x256x56x56x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+128
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+128
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+16
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+16
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x56x56x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x56x56x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+16
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x56x56x1x3x3x1x30x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x3x3x1x44x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x44x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x56x1x3x3x1x512x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x56x56x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x3x3x1x88x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8
2x256x56x56x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x5x5x1x128x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x56x56x1x5x5x1x512x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x56x56x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x56x56x1x7x7x1x128x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x56x56x1x7x7x1x256x1x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x56x56x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x571x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x571x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x571x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x571x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x578x39x1x3x3x1x1x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x578x39x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x579x39x1x3x3x1x1x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x579x39x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x57x57x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x57x57x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x57x57x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x256x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 1, 1, 1>+1
2x256x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x57x57x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x57x57x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x57x57x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x57x57x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x57x57x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x256x57x57x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x57x57x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x57x57x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x57x57x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x583x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x583x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x583x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x583x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x58x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x58x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x58x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x58x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x58x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x58x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x58x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x58x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x58x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x58x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x58x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x58x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x58x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x58x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x58x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x58x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x58x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x58x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x58x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x58x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x58x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x58x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x58x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x58x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x58x58x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x58x58x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x58x58x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x58x58x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x58x58x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x256x58x58x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x58x58x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x58x58x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x58x58x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x58x58x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x256xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x58x58x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x58x58x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x58x58x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x590x19x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x590x19x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x592x592x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x593x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x593x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x593x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x593x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x59x59x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x59x59x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x59x59x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x5x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x5x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x5x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:90
2x256x5x5x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:60
2x256x5x5x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:77
2x256x5x5x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:147
2x256x5x5x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x5x5x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:4
2x256x5x5x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:32
2x256x5x5x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:5
2x256x5x5x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x5x5x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:33
2x256x5x5x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:44
2x256x5x5x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:126
2x256x5x5x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:125
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];TransposedConvBinWinoRxS<3-2>:134
2x256x5x5x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43
2x256x5x5x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:136
2x256x5x5x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:141
2x256x5x5x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x5x5x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x256x5x5x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:26
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];TransposedConvBinWinoRxS<3-2>:24
2x256x5x5x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51
2x256x5x5x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];TransposedConvBinWinoRxS<3-2>:26
2x256x5x5x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x5x5x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:55
2x256x5x5x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];TransposedConvBinWinoRxS<3-2>:17
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];TransposedConvBinWinoRxS<3-2>:11
2x256x5x5x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54
2x256x5x5x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];TransposedConvBinWinoRxS<3-2>:27
2x256x5x5x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x256x5x5x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];TransposedConvBinWinoRxS<3-2>:118
2x256x5x5x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x256x5x5x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x5x5x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:82
2x256x5x5x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x256x5x5x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x5x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x5x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x486x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:227
2x256x5x5x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:243
2x256x5x5x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x256x5x5x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:49
2x256x5x5x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:21
2x256x5x5x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:65
2x256x5x5x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:31
2x256x5x5x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x256x5x5x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x5x5x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:121
2x256x5x5x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x510x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:139
2x256x5x5x1x3x3x1x510x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x5x5x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x5x5x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x5x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x5x5x1x3x3x1x512x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x5x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,5,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x5x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x5x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x7x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x5x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x8x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x8x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x5x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x5x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x5x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x5x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x5x9x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x9x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x5x9x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x609x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x609x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x609x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x609x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x60x19x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x60x19x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x60x19x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x60x19x1x3x3x1x256x294x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x60x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x60x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x60x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x60x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x60x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x60x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x60x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x60x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x60x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x60x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x60x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x60x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x60x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x60x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x60x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x60x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x60x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x60x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x60x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x60x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x60x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x60x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x60x44x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x44x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x60x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x60x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x60x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x60x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x60x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x60x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x60x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x60x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x60x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x60x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x60x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x60x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x611x39x1x3x3x1x1x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x611x39x1x3x3x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x612x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x612x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x612x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x612x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x615x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x615x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x615x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x615x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x61x19x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x61x19x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x61x19x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x61x19x1x3x3x1x256x274x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x622x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x622x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x622x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x622x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x622x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x622x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x622x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x622x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x623x39x1x3x3x1x1x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x623x39x1x3x3x1x1x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x623x39x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x623x39x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x62x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x62x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x40x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x62x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x62x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x62x40x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x62x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x40x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x40x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x62x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x62x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x62x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x62x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x62x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x62x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x62x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x62x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x62x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x62x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x62x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x62x46x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x62x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x62x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x62x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x62x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x62x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x62x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x62x48x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x48x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x62x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x62x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x62x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x62x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x62x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x62x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x62x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x62x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x62x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x62x62x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x630x39x1x3x3x1x1x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x630x39x1x3x3x1x1x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x630x39x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x630x39x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x632x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x632x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x632x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x632x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x633x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x633x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x633x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x633x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x640x640x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x640x640x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x641x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x641x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x641x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x641x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x642x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x642x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x642x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x642x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x643x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x643x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x643x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x643x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x644x39x1x3x3x1x1x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x644x39x1x3x3x1x1x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x644x39x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x644x39x1x3x3x1x256x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x649x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x649x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x649x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x649x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x64x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x64x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x64x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x64x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x64x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x64x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x64x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x64x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x64x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x64x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x64x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x64x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x64x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x64x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x64x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x64x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x64x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x64x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x64x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x64x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x64x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x64x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x46x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x46x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x64x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x64x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x256x64x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x64x64x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x256x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x64x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6]
2x256x64x64x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x64x64x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x64x64x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x64x64x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x256x64x64x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x64x64x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x256x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x64x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x155x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x64x64x1x3x3x1x225x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x256x64x64x1x3x3x1x232x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x64x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x64x64x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x64x64x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x256x64x64x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x64x64x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x64x64x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x256x64x64x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x64x64x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x64x64x1x5x5x1x256x1x2x2x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x256x64x64x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x655x39x1x3x3x1x1x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x655x39x1x3x3x1x1x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x655x39x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x655x39x1x3x3x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x65x19x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x65x19x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x65x19x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x65x19x1x3x3x1x256x299x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x660x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x660x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x660x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x660x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x662x39x1x3x3x1x1x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x662x39x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x666x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x666x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x666x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x666x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x66x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x66x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x66x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x66x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x66x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x66x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x66x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x66x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x66x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x66x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x66x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x66x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x66x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x66x44x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x66x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x66x44x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x66x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x66x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x66x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x66x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x66x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x66x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x66x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x66x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x66x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x66x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x66x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x66x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x66x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x66x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x66x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x66x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x66x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x66x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x66x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x66x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x671x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x671x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x671x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x671x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x673x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x673x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x673x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x673x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x674x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x674x39x1x3x3x1x1x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x674x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x674x39x1x3x3x1x256x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x676x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x676x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x676x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x676x39x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x676x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x676x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x676x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x676x39x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x680x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x680x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x680x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x680x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x688x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x688x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x688x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x688x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x68x19x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x68x19x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x68x19x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x68x19x1x3x3x1x256x237x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x68x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x68x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x68x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x68x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x68x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x68x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x68x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x68x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x68x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x68x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x68x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x68x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x68x44x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x68x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x68x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x68x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x68x44x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x44x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x68x44x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x68x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x68x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x68x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x68x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x68x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x68x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x68x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x68x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x68x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x68x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x68x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x68x50x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x50x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x68x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x693x39x1x3x3x1x1x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x693x39x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x69x39x1x3x3x1x1x329x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x69x39x1x3x3x1x256x329x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x69x69x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x256x69x69x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x69x69x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x69x69x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x69x69x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x69x69x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x69x69x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x69x69x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x69x69x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x69x69x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x69x69x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x69x69x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x6x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,5,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x6x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x6x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x11x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x6x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x6x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x5x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x6x6x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x6x6x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x6x6x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x6x6x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x6x6x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x6x6x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x6x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x6x6x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x6x6x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x6x6x1x3x3x1x2048x128x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x6x6x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x6x6x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x2048x16x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x6x6x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x6x6x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x6x6x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x6x6x1x3x3x1x2048x1x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x2048x256x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x6x6x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x6x6x1x3x3x1x2048x2x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x2048x32x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x6x6x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x6x6x1x3x3x1x2048x4x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x6x6x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x6x6x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x2048x512x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x2048x64x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x256x6x6x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x2048x8x12x12x0x1x1x0x12x12x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x6x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x6x6x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x6x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x7x1x3x3x1x256x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x6x7x1x3x3x1x256x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x6x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x6x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x7x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x7x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x6x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x6x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x8x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x6x8x1x3x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x6x8x1x3x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x6x8x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x6x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x6x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x6x9x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x6x9x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x700x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x700x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x700x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x700x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x708x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x708x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x708x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x708x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x70x19x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x70x19x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x70x19x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x70x19x1x3x3x1x256x291x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x70x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x70x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x70x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x70x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x70x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x70x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x70x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x70x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x70x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x70x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x70x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x70x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x70x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x70x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x70x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x70x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x70x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x70x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x70x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x70x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x70x70x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x256x70x70x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x256x70x70x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x70x70x1x3x3x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x70x70x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x256x70x70x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x70x70x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x256x70x70x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x256x70x70x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x256x70x70x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x70x70x1x3x3x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x70x70x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x70x70x1x3x3x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x716x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x716x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x716x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x716x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x721x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x721x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x721x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x721x19x1x3x3x1x256x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x721x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x721x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x721x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x721x19x1x3x3x1x256x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x722x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x722x39x1x3x3x1x1x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x722x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x722x39x1x3x3x1x256x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x723x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x723x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x724x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x724x39x1x3x3x1x1x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x724x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x724x39x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x727x39x1x3x3x1x1x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x727x39x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x72x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x72x168x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x168x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x72x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x72x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x72x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x72x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x72x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x72x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x72x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x72x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x72x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x72x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x46x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x72x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x72x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x72x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x72x46x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x46x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x72x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x72x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x72x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x72x48x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x48x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x72x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x72x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x72x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x72x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x72x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x72x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x72x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x72x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x72x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x72x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x72x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x731x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x731x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x731x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x731x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x731x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x731x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x731x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x731x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x738x39x1x3x3x1x1x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x738x39x1x3x3x1x256x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x745x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x745x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x747x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x747x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x747x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x747x19x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x74x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x74x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x74x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x74x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x74x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x74x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x74x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x74x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x74x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x44x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x74x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x74x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x74x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x74x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x74x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x74x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x74x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x74x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x74x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x74x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x74x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x74x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x74x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x74x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x74x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x74x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x74x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x752x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x752x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x759x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x759x39x1x3x3x1x1x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x759x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x759x39x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x75x112x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x75x112x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x75x112x1x1x1x1x128x1x0x0x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x75x112x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x75x112x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x75x112x1x3x3x1x128x1x1x1x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x75x112x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x75x112x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x256x75x112x1x5x5x1x128x1x2x2x0x3x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x764x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x764x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x767x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x767x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x768x768x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x256x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x768x768x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x256x768x768x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1]
2x256x768x768x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254
2x256x769x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x769x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x76x19x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x76x19x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x76x19x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x76x19x1x3x3x1x256x222x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x76x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x76x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x76x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x76x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x76x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x76x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x76x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x76x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x76x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x76x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x76x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x76x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x76x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x76x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x76x48x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x48x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x76x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x76x48x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x76x48x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x76x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x76x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,32,32,32,2,1,1,2,1,0,0,2,0,0,1,4,8,1,1,8,1,16,1,4,2,1,1,8,1,16,38[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x76x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x76x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x76x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x76x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x76x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x76x50x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x76x50x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x76x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x77x19x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x77x19x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x77x19x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x77x19x1x3x3x1x256x253x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x785x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x785x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x78x19x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x78x19x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x78x19x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x78x19x1x3x3x1x256x224x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x256x78x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x78x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x78x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x78x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x78x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x78x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x78x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x78x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x78x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x78x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x78x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x78x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x78x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x78x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x78x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x78x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x78x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x78x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x78x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x78x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x78x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x78x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x78x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x78x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x78x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x78x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x78x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x78x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x78x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x78x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x78x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x78x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x78x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x78x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x799x1087x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x799x1087x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x799x1215x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x799x1215x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x7x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x7x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x7x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x10x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x10x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x10x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x7x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x7x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x7x11x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x11x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x7x12x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x7x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x7x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x5x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x5x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x5x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x7x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x7x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x7x7x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x7x7x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x256x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x256x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x256x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x7x7x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x256x7x7x1x7x7x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x7x7x1x7x7x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x7x7x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x400x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x7x7x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x7x7x1x7x7x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x256x7x7x1x7x7x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x7x7x1x7x7x1x1024x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x7x7x1x7x7x1x1024x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x7x7x1x7x7x1x1024x800x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x7x7x1x7x7x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x1024x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x7x7x1x7x7x1x256x4x3x3x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x7x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x8x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x8x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x7x9x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x7x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x7x9x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x7x9x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x800x1088x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x800x1088x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x800x1216x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x800x1216x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x804x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x804x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x104x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x108x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x108x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x108x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x108x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x108x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x108x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x108x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x80x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x80x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x80x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x112x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x80x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x120x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x120x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x120x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x124x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x80x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x124x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x80x124x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x124x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x80x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x80x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67
2x256x80x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x128x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+128
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x256x80x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x132x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x132x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x80x132x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x136x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x80x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x80x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x80x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x144x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x80x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x144x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x144x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x80x144x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x80x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x148x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x148x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x80x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x80x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x152x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x156x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x80x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x160x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x164x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x80x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x164x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x168x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x80x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x80x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x80x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x80x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x80x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x44x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x80x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x80x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x46x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x80x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x80x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x80x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x80x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x80x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x80x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x80x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x80x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x80x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x80x80x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x80x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x80x80x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x80x80x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x80x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x80x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x80x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x80x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x814x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x814x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x818x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x818x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x81x19x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x81x19x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x81x19x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x81x19x1x3x3x1x256x199x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x81x39x1x3x3x1x1x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x81x39x1x3x3x1x1x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x81x39x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x81x39x1x3x3x1x256x418x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x82x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x82x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x82x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x82x40x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x82x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x82x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x82x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x82x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x82x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x82x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x82x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x82x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x82x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x82x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x82x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x82x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x82x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x82x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x82x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x82x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x50x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x82x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x832x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x832x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x832x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x832x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x833x39x1x3x3x1x1x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x833x39x1x3x3x1x256x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x83x19x1x3x3x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x83x19x1x3x3x1x256x116x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x840x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x840x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x104x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x104x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x104x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x84x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x84x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x104x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x104x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x108x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x84x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x108x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x108x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x84x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x112x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x112x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x112x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x112x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x84x112x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x116x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x84x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x116x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x116x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x116x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x84x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x120x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x84x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x84x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x84x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x84x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x128x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x128x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x128x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x128x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x84x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x132x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x132x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x132x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x84x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x136x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x136x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x84x140x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x140x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x140x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x140x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x84x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x144x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x148x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x84x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x152x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x152x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x156x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x156x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x84x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x160x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x84x164x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x84x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x168x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x84x168x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x84x168x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x84x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x40x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x40x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x40x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x40x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x84x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x84x40x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x256x84x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x84x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x42x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x42x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x84x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x256x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x42x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x42x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x42x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x84x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x44x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x44x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x84x44x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x84x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x46x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x46x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x46x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x84x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x48x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x84x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x84x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x48x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x84x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x48x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x84x50x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x50x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x50x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x256x84x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x84x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x50x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x84x84x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x84x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x84x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x84x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x84x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x84x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x84x84x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x84x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x84x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x84x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x855x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x855x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x855x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x855x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x856x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x856x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x85x19x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x85x19x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x85x19x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x85x19x1x3x3x1x256x181x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x85x19x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x85x19x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x85x19x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x85x19x1x3x3x1x256x189x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x873x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x873x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x873x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x873x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x874x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x874x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x100x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x100x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x88x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x100x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x88x108x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x108x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x88x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x108x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x108x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x88x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x112x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x88x116x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x116x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x88x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x116x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x116x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x88x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x120x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x88x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x120x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x88x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x120x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x88x120x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x88x120x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x124x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x124x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x88x124x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x88x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x128x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x88x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x88x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x88x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x128x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x132x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x132x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x88x132x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x88x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x88x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x88x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x88x132x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x132x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x88x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x136x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x140x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x140x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x140x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x88x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x144x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x88x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x144x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x88x148x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x148x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x88x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x148x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x152x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x152x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x88x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x152x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x156x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x156x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x88x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x88x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x88x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x156x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x160x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x160x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x88x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x164x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x88x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x88x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x88x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x168x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x88x168x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x88x19x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x88x19x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x88x19x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x256x88x19x1x3x3x1x256x155x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x88x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x80x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x88x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x256x88x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x88x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x88x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x88x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x88x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x88x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x88x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x88x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x88x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x895x799x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x895x799x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x896x800x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x896x800x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x8x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x8x10x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x8x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x8x11x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x8x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x4x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x256x8x4x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x4x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x4x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x256x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x8x5x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x8x5x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x5x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x5x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x5x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x8x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x6x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x6x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x6x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x8x6x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x8x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x8x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x7x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x8x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x256x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x256x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x256x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x256x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x256x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x256x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x256x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x1x3x1x512x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x1x3x1x512x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x512x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x1x3x1x512x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x1x3x1x512x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x1x3x1x512x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x1x3x1x512x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x1x3x1x512x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x256x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x8x8x1x3x1x1x384x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x256x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x256x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x8x8x1x3x1x1x384x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x256x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x256x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x3x1x1x512x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x8x8x1x3x1x1x512x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x256x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x256x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x1x1x512x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x3x1x1536x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x8x8x1x3x3x1x1536x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x3x3x1x512x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x256x8x8x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x8x8x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x8x8x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x8x8x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x8x8x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x8x8x1x4x4x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x8x8x1x4x4x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x8x8x1x4x4x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x8x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x256x8x9x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x907x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x907x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x907x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x907x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x910x39x1x3x3x1x1x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x910x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x918x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x918x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x918x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x918x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x91x39x1x3x3x1x1x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,3,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x91x39x1x3x3x1x1x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,4,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x256x91x39x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x91x39x1x3x3x1x256x543x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x925x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x925x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x925x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x925x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x927x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x927x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x92x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x108x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x92x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x116x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x92x116x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x120x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x120x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x92x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x124x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x124x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x124x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x124x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x124x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x92x124x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x92x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x128x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x128x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x132x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x132x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x92x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x136x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x136x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x140x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x140x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x140x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x140x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x140x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x140x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x140x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x140x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x92x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x144x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x148x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x148x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x256x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x148x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x92x148x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x148x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x152x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x152x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x92x152x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x92x156x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x156x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x156x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x92x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x160x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x256x92x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x256x92x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x160x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x164x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x164x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x164x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x92x164x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x164x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x92x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x92x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x168x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x168x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x92x168x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x168x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x92x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x92x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x92x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x92x88x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x92x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x92x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x92x92x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x92x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x92x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x92x92x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x92x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x92x92x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x92x92x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x932x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x932x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x932x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x932x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x937x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x937x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x937x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x937x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x941x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x941x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x945x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x945x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x945x39x1x3x3x1x1x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x945x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x945x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x945x39x1x3x3x1x256x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x104x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x104x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x104x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x104x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x104x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x96x108x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x108x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x108x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x108x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x112x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x112x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x112x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x112x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x96x112x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x96x116x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x96x116x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x256x96x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x116x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x256x96x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x116x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x116x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x116x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x96x116x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x96x120x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x120x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x96x120x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x120x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x96x124x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x124x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x96x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x124x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x128x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x96x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x96x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x256x96x128x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x128x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x128x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x132x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x132x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x132x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x96x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x132x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x136x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x136x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x96x136x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x140x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x140x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x140x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x96x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x96x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x140x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x144x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x144x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x144x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x144x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x144x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x144x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x96x148x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x148x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x148x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x148x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x148x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x148x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x256x96x148x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x148x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x256x96x152x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x256x96x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x152x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x256x96x156x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x156x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x156x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x96x156x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x256x96x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x256x96x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x156x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x156x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x160x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x160x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x160x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x96x160x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x96x160x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x256x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x160x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x160x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x160x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x96x160x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x96x164x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x164x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x256x96x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x256x96x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x164x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x96x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x96x168x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x96x168x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x256x96x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x168x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x168x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x19x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x96x19x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x96x19x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x96x19x1x3x3x1x256x143x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x96x19x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x96x19x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x96x19x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x96x19x1x3x3x1x256x171x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x96x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x256x96x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x84x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x84x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x256x96x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x96x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x256x96x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x256x96x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x88x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x256x96x96x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x96x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x96x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x256x96x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x256x96x96x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x256x96x96x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x96x96x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x96x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x96x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x96x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x256x96x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x256x96x96x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x256xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x256x96x96x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x96x96x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x256x96x96x1x7x7x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x256x972x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x972x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x973x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x973x39x1x3x3x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x973x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x973x39x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x976x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x976x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x981x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x981x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x256x983x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x983x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x988x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x988x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x989x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x989x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x98x19x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x256x98x19x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x256x98x19x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x98x19x1x3x3x1x256x172x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x995x39x1x3x3x1x1x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x256x995x39x1x3x3x1x256x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x256x99x19x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x99x19x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x99x19x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x256x99x19x1x3x3x1x256x170x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x256x9x13x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x15x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x9x17x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x256x9x21x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x256x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x9x21x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x21x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x21x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x21x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x256x9x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x9x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x9x5x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x9x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x9x6x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x9x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x9x6x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x256x9x6x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x6x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x256x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x256x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x9x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x256x9x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x9x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x9x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x256x9x7x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x7x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[5];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x256x9x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x256x9x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x256x9x9x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x256x9x9x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x9x9x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x256x9x9x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x256x9x9x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x256x9x9x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x25x128x128x1x1x1x1x278x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x25x14x14x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x25x56x56x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x25x56x56x1x1x1x1x26x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x260x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x260x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x260x64x64x1x1x1x1x1560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x260x7x7x1x1x1x1x1560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x261x128x128x1x3x3x1x261x1x1x1x0x1x1x0x1x1x0x0x261xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x261x14x14x1x1x1x1x93x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x261x14x14x1x3x3x1x261x1x1x1x0x1x1x0x1x1x0x0x261xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x261x64x64x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x264x1x1x1x1x1x1x1056x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x264x64x64x1x1x1x1x1320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x264x7x7x1x1x1x1x1320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x264x7x7x1x1x1x1x1584x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2688x11x11x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x2688x14x14x1x5x5x1x2688x1x2x2x0x1x1x0x1x1x0x0x2688xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2688x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x2688x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2688x16x16x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x2688x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x2688x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2688x16x16x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x2688x1x1x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2688x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x2688x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2688x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x2688x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,7,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[7];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x2688x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2688x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x2688x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2688x32x32x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2688x64x64x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2688x64x64x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2688x7x7x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2688x7x7x1x3x3x1x2688x4x1x1x0x1x1x0x1x1x0x0x2688xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x268x14x14x1x1x1x1x124x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x268x14x14x1x3x3x1x268x4x1x1x0x1x1x0x1x1x0x0x268xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x268x64x64x1x1x1x1x124x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x26x1x1x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x26x1x1x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x26x1x1x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x256x256x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x512x512x1x1x1x1x53x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x512x512x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x512x512x1x1x1x1x81x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x512x512x1x3x3x1x26x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x26x56x56x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x56x56x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x56x56x1x1x1x1x81x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x26x56x56x1x3x3x1x26x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x270x56x56x1x1x1x1x108x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2718x64x64x1x1x1x1x487x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2718x64x64x1x3x3x1x2718x1x1x1x0x1x1x0x1x1x0x0x2718xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2718x7x7x1x1x1x1x487x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x272x12x12x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x272x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x272x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x272x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x272x16x16x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x272x16x16x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x272x16x16x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x272x16x16x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x272x16x16x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x272x16x16x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x272x16x16x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x272x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x272x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x272x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x272x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x272x64x64x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x272x7x7x1x1x1x1x1632x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x272x7x7x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x274x14x14x1x1x1x1x85x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x274x14x14x1x3x3x1x274x1x1x1x0x1x1x0x1x1x0x0x274xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2752x14x14x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2752x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2778x1x1x1x1x1x1x28280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x2778x1x1x1x1x1x1x28280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x277x64x64x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x277x64x64x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x277x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x277x7x7x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x278x128x128x1x1x1x1x230x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x128x128x1x1x1x1x245x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x128x128x1x1x1x1x250x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x128x128x1x1x1x1x253x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x128x128x1x1x1x1x255x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x128x128x1x1x1x1x499x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x14x14x1x1x1x1x238x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x14x14x1x1x1x1x255x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x14x14x1x1x1x1x255x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x64x64x1x1x1x1x2042x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x278x64x64x1x1x1x1x244x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x278x64x64x1x1x1x1x254x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x64x64x1x1x1x1x255x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x64x64x1x1x1x1x499x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x278x7x7x1x1x1x1x2042x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x27x113x113x1x3x3x1x27x1x0x0x0x2x2x0x1x1x0x0x27xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x27x512x512x1x1x1x1x162x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x27x56x56x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x27x56x56x1x1x1x1x26x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x280x128x128x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x280x14x14x1x3x3x1x280x4x1x1x0x1x1x0x1x1x0x0x280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x280x256x256x1x5x5x1x280x1x2x2x0x2x2x0x1x1x0x0x280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x280x28x28x1x5x5x1x280x1x2x2x0x2x2x0x1x1x0x0x280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x280x32x32x1x3x3x1x280x1x1x1x0x1x1x0x1x1x0x0x280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x280x64x64x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x280x64x64x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x280x64x64x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x280x64x64x1x3x3x1x280x1x1x1x0x1x1x0x1x1x0x0x280xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2816x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2816x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2816x32x32x1x3x3x1x2816x1x1x1x0x1x1x0x1x1x0x0x2816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2816x64x64x1x1x1x1x11264x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2816x64x64x1x1x1x1x5637x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x2816x7x7x1x1x1x1x11264x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2816x7x7x1x1x1x1x2816x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2816x7x7x1x1x1x1x5636x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2816x7x7x1x1x1x1x5637x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x2816x7x7x1x3x3x1x2816x1x1x1x0x1x1x0x1x1x0x0x2816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2816x7x7x1x7x7x1x2816x1x3x3x0x1x1x0x1x1x0x0x2816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2816x7x7x1x7x7x1x2816x4x3x3x0x1x1x0x1x1x0x0x2816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2816x7x7x1x9x9x1x2816x4x4x4x0x1x1x0x1x1x0x0x2816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x28280x64x64x1x1x1x1x28280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x28280x64x64x1x3x3x1x28280x1x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x28280x7x7x1x1x1x1x28280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2880x131x131x1x5x5x1x2880x1x0x0x0x2x2x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2880x131x131x1x5x5x1x2880x4x0x0x0x2x2x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2880x14x14x1x5x5x1x2880x1x2x2x0x1x1x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2880x17x17x1x5x5x1x2880x1x0x0x0x2x2x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2880x17x17x1x5x5x1x2880x4x0x0x0x2x2x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x2880x1x1x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2880x1x1x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2880x32x32x1x1x1x1x824x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2880x64x64x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2880x64x64x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2880x7x7x1x3x3x1x2880x4x1x1x0x1x1x0x1x1x0x0x2880xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x1024x1024x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x125x125x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x128x128x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x128x128x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x128x128x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x128x128x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x128x128x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x128x128x1x3x3x1x304x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x128x128x1x7x7x1x288x4x3x3x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x128x128x1x9x9x1x288x1x4x4x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x130x130x1x3x3x1x288x4x0x0x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x139x139x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x139x139x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x288x140x140x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x140x140x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x140x140x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x140x140x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x140x140x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x141x141x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x288x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x288x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x288x14x14x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x288x14x14x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x14x14x1x3x3x1x144x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x288x14x14x1x3x3x1x144x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x3x3x1x144x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x288x14x14x1x3x3x1x144x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x288x14x14x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x288x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x288x14x14x1x3x3x1x144x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x288x14x14x1x3x3x1x144x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x288x14x14x1x3x3x1x144x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x288x14x14x1x3x3x1x144x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x14x14x1x3x3x1x144x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x288x14x14x1x3x3x1x144x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x288x14x14x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x288x14x14x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x288x14x14x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x14x14x1x3x3x1x144x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x288x14x14x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x14x14x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x288x14x14x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x14x14x1x5x5x1x288x4x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x14x14x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x150x150x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x150x150x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x150x150x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x153x153x1x5x5x1x288x4x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x19x19x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x144x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x144x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x144x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x144x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x144x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x144x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x144x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x144x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x144x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x24x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x288x24x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x24x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x24x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x24x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x288x24x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x24x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x24x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x288x24x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x24x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x288x24x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x288x24x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x24x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+16
2x288x24x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x288x24x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x288x24x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x288x24x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x288x24x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x288x24x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x288x24x16x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x96x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x1x1x1x96x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x288x24x16x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x96x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x96x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x288x24x16x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x96x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x288x24x16x1x1x1x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x288x24x16x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x1x1x96x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x288x24x16x1x1x1x1x96x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x24x16x1x1x1x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x1x1x1x96x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x288x24x16x1x1x1x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x1x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x1x1x1x96x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x1x1x96x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x1x3x1x288x10x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x10x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x10x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x11x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x11x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x11x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x12x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x12x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x12x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x13x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x13x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x13x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x14x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x14x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x14x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x15x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x15x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x15x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x17x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x17x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x17x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x18x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x18x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x18x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x19x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x19x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x19x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x1x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x288x24x16x1x1x3x1x288x1x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x1x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x1x3x1x288x20x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x20x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x20x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x21x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x21x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x21x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x22x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x22x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x22x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x23x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x23x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x23x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x1x3x1x288x25x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x25x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x3x1x288x25x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x26x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x26x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x26x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x27x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x27x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x27x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x28x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x28x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x28x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x29x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x29x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x29x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x2x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x2x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x2x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x1x3x1x288x30x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x30x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x30x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x31x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x31x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x3x1x288x31x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x33x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x33x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x33x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x34x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x34x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x3x1x288x34x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x35x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x35x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x35x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x36x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x36x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x1x3x1x288x36x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x37x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x37x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x37x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x1x3x1x288x3x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x1x3x1x288x3x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x3x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x1x3x1x288x4x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x4x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x1x3x1x288x4x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x5x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x5x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x5x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x6x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x6x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x6x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x7x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x7x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x7x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x1x3x1x288x9x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x1x3x1x288x9x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x1x3x1x288x9x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x10x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x10x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x10x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x11x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x11x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x11x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x12x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x12x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x12x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x13x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x13x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x13x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x14x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x14x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x14x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x15x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x15x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x15x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x17x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x17x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x17x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x18x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x18x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x18x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x19x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x19x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x19x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x1x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x1x1x288x1x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x1x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x1x1x288x20x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x20x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x20x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x21x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x21x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x21x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x22x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x22x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x22x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x23x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x23x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x23x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x288x24x16x1x3x1x1x288x25x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x25x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x25x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x26x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x26x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x26x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x27x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x27x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x27x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x28x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x28x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x28x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x29x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x29x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x24x16x1x3x1x1x288x29x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x2x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x1x1x288x2x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x2x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x1x1x288x30x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x30x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x3x1x1x288x30x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x31x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x31x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x24x16x1x3x1x1x288x31x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x33x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x24x16x1x3x1x1x288x33x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x33x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x34x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x34x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x34x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x35x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x35x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x35x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x288x24x16x1x3x1x1x288x36x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x36x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x36x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x37x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x37x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x37x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x1x1x288x3x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x3x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x3x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x4x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x4x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x24x16x1x3x1x1x288x4x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x5x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x5x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x5x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x6x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x6x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x6x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x7x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x7x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x3x1x1x288x7x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x1x1x288x9x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x1x1x288x9x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x1x1x288x9x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x10x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x10x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x11x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x11x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x12x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x12x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x13x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x13x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x14x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x14x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x15x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x15x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x288x24x16x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x17x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x17x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x18x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x18x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x19x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x19x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x288x24x16x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x288x24x16x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x20x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x20x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x21x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x21x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x22x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x22x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x288x24x16x1x3x3x1x288x23x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x23x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x288x24x16x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x24x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x24x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x25x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x25x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x26x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x26x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x27x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x27x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x28x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x28x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x29x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x29x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x288x24x16x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x24x16x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x30x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x30x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x31x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x31x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x33x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x33x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x288x24x16x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x34x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x34x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x24x16x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x35x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x35x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x24x16x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x36x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x36x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x24x16x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x37x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x37x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x24x16x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x288x24x16x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x288x24x16x1x3x3x1x288x3x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x24x16x1x3x3x1x288x3x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x288x24x16x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x288x24x16x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x5x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x5x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x6x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x6x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x7x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x7x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x288x24x16x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x24x16x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x24x16x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x24x16x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x288x24x16x1x3x3x1x288x9x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x24x16x1x3x3x1x288x9x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x253x253x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x253x253x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x253x253x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x256x256x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x256x256x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x256x256x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x288x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x288x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x28x28x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x29x29x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x32x32x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x32x32x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x32x32x1x5x5x1x288x1x2x2x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x33x33x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x33x33x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x33x33x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x34x34x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x34x34x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x34x34x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x34x34x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x34x34x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x34x34x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x48x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x288x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x35x35x1x3x3x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x288x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,93[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x35x35x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x39x39x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x48x32x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x288x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x288x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x288x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x288x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x288x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x288x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x288x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x288x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x288x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+64
2x288x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x288x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x288x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x288x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x288x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x288x48x32x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x10x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x11x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x12x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x13x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x14x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x15x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x17x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x18x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x48x32x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x19x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x288x48x32x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x48x32x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x20x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x288x48x32x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x21x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x22x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x23x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x24x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x3x3x1x288x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x25x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x26x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x27x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x288x48x32x1x3x3x1x288x28x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x29x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x288x48x32x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x48x32x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x30x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x31x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x288x48x32x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x288x48x32x1x3x3x1x288x33x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x288x48x32x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x34x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x35x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x288x48x32x1x3x3x1x288x36x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x37x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x3x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x48x32x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x5x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x48x32x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x6x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x288x48x32x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x7x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x48x32x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x288x48x32x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x48x32x1x3x3x1x288x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x288x48x32x1x3x3x1x288x9x1x1x0x2x2x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x4x1024x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x4x1024x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x4x1024x1x1x1x1x577x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x288x4x4096x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x4x4096x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x4x49x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x512x512x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x512x512x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x512x512x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x512x512x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x288x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x288x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x288x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x288x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x288x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x288x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x288x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x56x56x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x56x56x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x56x56x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x288x64x128x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x288x64x64x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x64x64x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x64x64x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x64x64x1x1x1x1x672x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x64x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x288x64x64x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x64x64x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x64x64x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x288x64x64x1x9x9x1x288x1x4x4x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x65x65x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x67x67x1x5x5x1x288x1x0x0x0x2x2x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x72x72x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x72x72x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x288x7x7x1x1x1x1x1440x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x288x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x288x7x7x1x3x3x1x288x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x288x7x7x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x288x7x7x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x288x7x7x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x288x7x7x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x32x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x288x7x7x1x5x5x1x288x4x2x2x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x288x7x7x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x288x7x7x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x288x7x7x1x5x5x1x288x64x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x288x7x7x1x7x7x1x288x4x3x3x0x1x1x0x1x1x0x0x288xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x289x64x64x1x1x1x1x2042x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x28x1024x1024x1x3x3x1x28x1x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x28x112x112x1x3x3x1x28x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x112x112x1x3x3x1x28x4x1x1x0x1x1x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvDepthwiseFwd2D:DeviceGroupedConvFwd<2, 64, BlockTileSize: 112, 112, FilterSize: 3,3, Dilation: 1, 1, Stride: 1, 1, Pad: 1, 1, NBatch: 2, SubTileH: 14, SubTileW: 16, InVectorWidth: 8, OutVectorWidth: 8, RequirePadding: 0>;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x28x128x128x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x128x128x1x3x3x1x28x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x201x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x1x1x1x1x1x1x201x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x1x1x1x1x1x1x213x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x28x1x1x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x28x1x1x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
2x28x1x1x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x1x1x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x28x1x1x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x28x1x1x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+1
2x28x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x256x256x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x28x256x256x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x28x256x256x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x256x256x1x1x1x1x44x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x256x256x1x3x3x1x28x1x1x1x0x1x1x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x28x28x28x1x3x3x1x28x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x28x28x1x3x3x1x28x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x512x512x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x512x512x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x512x512x1x3x3x1x28x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x512x512x1x3x3x1x56x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x512x512x1x5x5x1x28x1x2x2x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x28x56x56x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x28x56x56x1x5x5x1x28x4x2x2x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x2904x128x128x1x1x1x1x7392x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2904x128x128x1x3x3x1x2904x1x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2904x14x14x1x1x1x1x2904x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2904x14x14x1x1x1x1x7392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2904x1x1x1x1x1x1x264x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2904x256x256x1x3x3x1x2904x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2904x28x28x1x3x3x1x2904x1x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2904x64x64x1x1x1x1x7392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2922x32x32x1x1x1x1x520x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x292x128x128x1x3x3x1x292x4x1x1x0x1x1x0x1x1x0x0x292xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x292x14x14x1x1x1x1x85x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x292x14x14x1x3x3x1x292x1x1x1x0x1x1x0x1x1x0x0x292xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x292x1x1x1x1x1x1x22x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x296x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x296x64x64x1x5x1x1x296x4x2x0x0x1x1x0x1x1x0x0x296xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x296x7x7x1x1x5x1x296x1x0x2x0x1x1x0x1x1x0x0x296xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x296x7x7x1x1x5x1x296x4x0x2x0x1x1x0x1x1x0x0x296xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x2976x64x64x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x2976x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x29x1x1x1x1x1x1x348x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x100x743x1x1x1x1x2x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,1,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x2x100x743x1x1x1x1x2x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x100x743x1x1x1x1x2x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2x128x128x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x2x128x128x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x2x16x16x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x2x16x16x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;TransposedConvBinWinoRxS<3-2>:253
2x2x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;TransposedConvBinWinoRxS<3-2>:213
2x2x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:4
2x2x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;TransposedConvBinWinoRxS<3-2>:256
2x2x19x19x1x1x1x1x64x2048x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;TransposedConvBinWinoRxS<3-2>:196
2x2x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];TransposedConvBinWinoRxS<2-3>:8;TransposedConvBinWinoRxS<3-2>:2
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x2x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x2x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;TransposedConvBinWinoRxS<3-2>:256
2x2x19x19x1x1x1x1x64x4096x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;TransposedConvBinWinoRxS<3-2>:231
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:3
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;TransposedConvBinWinoRxS<3-2>:225
2x2x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:2;TransposedConvBinWinoRxS<3-2>:2
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;TransposedConvBinWinoRxS<3-2>:207
2x2x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:4
2x2x19x19x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x19x19x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x19x19x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x19x19x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x19x19x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x19x19x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x1x1x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x20x20x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x21x21x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x225x225x1x1x1x1x2x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x225x225x1x1x1x1x2x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x2x24x16x1x1x1x1x2x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x2x24x16x1x1x1x1x2x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x24x16x1x1x1x1x2x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x2x24x16x1x1x1x1x2x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x2x24x16x1x1x1x1x2x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x2x24x16x1x1x1x1x2x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x24x16x1x1x1x1x2x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x2x24x16x1x1x1x1x2x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x24x16x1x1x1x1x2x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x2x256x256x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x256x256x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,1,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x2x256x256x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x2x2x2x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x2x2x2x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x2x32x32x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x2x32x32x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x2x3x3x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x3x3x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x450x450x1x1x1x1x2x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x450x450x1x1x1x1x2x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x450x450x1x1x1x1x2x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x450x450x1x1x1x1x2x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x4x4x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x4x4x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x2x4x4x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x2x56x56x1x3x3x1x2x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x5x5x1x3x3x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x2x64x64x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x2x64x64x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x2x8x8x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x2x8x8x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x300x28x28x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x300x28x28x1x1x1x1x65x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x300x32x32x1x3x3x1x300x1x1x1x0x1x1x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x300x56x56x1x3x3x1x300x1x1x1x0x2x2x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x300x64x64x1x3x3x1x300x4x1x1x0x1x1x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x300x64x64x1x5x5x1x300x4x2x2x0x1x1x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x300x7x7x1x7x7x1x300x1x3x3x0x1x1x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x300x7x7x1x9x9x1x300x1x4x4x0x1x1x0x1x1x0x0x300xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3024x14x14x1x3x3x1x3024x1x1x1x0x2x2x0x1x1x0x0x27xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3024x64x64x1x1x1x1x3024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3024x7x7x1x1x1x1x3024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x304x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x304x128x128x1x1x1x1x304x4x0x0x0x1x1x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x128x128x1x3x3x1x304x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x304x128x128x1x3x3x1x304x1x1x1x0x1x1x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x304x128x128x1x3x3x1x304x4x1x1x0x1x1x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x304x128x128x1x7x7x1x608x1x3x3x0x2x2x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x128x128x1x7x7x1x608x4x3x3x0x2x2x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x130x130x1x3x3x1x304x1x0x0x0x2x2x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x304x14x14x1x3x3x1x304x1x1x1x0x1x1x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x14x14x1x3x3x1x304x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x304x14x14x1x7x7x1x608x1x3x3x0x2x2x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x15x15x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x304x1x1x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x304x256x256x1x1x1x1x76x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x304x256x256x1x3x3x1x304x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x304x512x512x1x1x1x1x76x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x304x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x304x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x304x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x304x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x304x64x64x1x3x3x1x608x1x1x1x0x2x2x0x1x1x0x0x304xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x304x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x12x12x1x3x3x1x3072x1x1x1x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x12x12x1x3x3x1x3072x4x1x1x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x16x16x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x16x16x1x3x3x1x3072x1x1x1x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x1x1x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[5];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x24x24x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x24x24x1x3x3x1x3072x4x1x1x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x25x25x1x3x3x1x3072x4x0x0x0x2x2x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x29x29x1x3x3x1x3072x1x0x0x0x2x2x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x33x33x1x3x3x1x3072x1x0x0x0x2x2x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x49x49x1x3x3x1x3072x4x0x0x0x2x2x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x64x64x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x65x65x1x3x3x1x3072x4x0x0x0x2x2x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x3072x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x3072x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3072x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3072x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x3072x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x3072x7x7x1x7x7x1x3072x1x3x3x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3072x8x8x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x3072x8x8x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x30x128x128x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x128x128x1x1x1x1x7x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x14x14x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x14x14x1x1x1x1x40x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x14x14x1x1x1x1x7x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x14x14x1x7x7x1x30x1x3x3x0x1x1x0x1x1x0x0x30xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x30x1x1x1x1x1x1x315x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x1x1x1x1x1x1x315x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x1x1x1x1x1x1x5x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x1x1x1x1x1x1x719x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x30x256x256x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x30x28x28x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x30x512x512x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x30x512x512x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x30x512x512x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x30x512x512x1x3x3x1x30x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x30x512x512x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x30x56x56x1x3x3x1x30x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x30x56x56x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x30x64x64x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x30x64x64x1x1x1x1x40x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x30x64x64x1x3x3x1x30x1x1x1x0x1x1x0x1x1x0x0x30xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3120x64x64x1x1x1x1x554x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x3120x7x7x1x1x1x1x554x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3120x7x7x1x3x3x1x3120x1x1x1x0x1x1x0x1x1x0x0x3120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x312x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x312x128x128x1x1x5x1x312x1x0x2x0x1x1x0x1x1x0x0x312xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x312x128x128x1x5x1x1x312x4x2x0x0x1x1x0x1x1x0x0x312xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x312x14x14x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x312x14x14x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x312x14x14x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x312x14x14x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x312x14x14x1x1x5x1x312x1x0x2x0x1x1x0x1x1x0x0x312xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x312x14x14x1x3x3x1x312x1x1x1x0x1x1x0x1x1x0x0x312xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x312x14x14x1x5x1x1x312x1x2x0x0x1x1x0x1x1x0x0x312xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x312x1x1x1x1x1x1x1248x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x312x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x315x128x128x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x315x128x128x1x5x5x1x315x1x2x2x0x1x1x0x1x1x0x0x315xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x315x128x128x1x5x5x1x315x4x2x2x0x1x1x0x1x1x0x0x315xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x315x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x315x64x64x1x5x5x1x315x1x2x2x0x1x1x0x1x1x0x0x315xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3168x1x1x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3168x7x7x1x3x3x1x3168x4x1x1x0x1x1x0x1x1x0x0x3168xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x318x128x128x1x1x1x1x1908x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x126x126x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x128x128x1x1x1x1x768x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x2x2x1x640x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x2x2x1x640x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x320x128x128x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x128x128x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x128x128x1x7x7x1x320x4x9x9x0x1x1x0x3x3x0x0x320xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x128x128x1x7x7x1x640x1x3x3x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x13x13x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x13x13x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x13x13x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x13x13x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x13x13x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x13x13x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x13x13x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x13x13x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x320x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x320x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x768x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x784x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x2x2x1x640x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x320x14x14x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x14x14x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x14x14x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x14x14x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x320x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x320x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x320x14x14x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x14x14x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x14x14x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x14x14x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x14x14x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x320x14x14x1x3x3x1x160x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x14x14x1x3x3x1x160x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x14x14x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x20xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x14x14x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x14x14x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x7x7x1x320x4x9x9x0x1x1x0x3x3x0x0x320xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x15x15x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x15x15x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x15x15x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x15x15x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x15x15x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x15x15x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x15x15x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x15x15x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x15x15x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x15x15x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x15x15x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x15x15x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x15x15x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x15x15x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x15x15x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x15x15x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x1x1x1x640x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x16x16x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x16x16x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x16x16x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x16x16x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x16x16x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x320x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x320x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x320x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x17x17x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x17x17x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x17x17x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x17x17x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x17x17x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x17x17x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x17x17x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x17x17x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x17x17x1x3x3x1x320x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x17x17x1x7x1x1x256x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x17x17x1x7x1x1x256x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x320x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x17x17x1x7x1x1x256x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x17x17x1x7x1x1x256x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x17x17x1x7x1x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x17x17x1x7x1x1x256x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x17x17x1x7x1x1x256x400x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x17x17x1x7x1x1x256x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x17x17x1x7x1x1x256x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x17x17x1x7x1x1x256x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x320x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x17x17x1x7x1x1x256x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x17x17x1x7x1x1x256x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x320x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x320x17x17x1x7x1x1x256x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x1x1x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x1x1x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x21x15x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x320x21x15x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x22x22x1x2x2x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x24x24x1x2x2x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x24x24x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x253x253x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x1x1x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x1x1x1x544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x320x256x256x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x25x13x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x25x13x1x3x3x1x256x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x25x25x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x28x28x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x28x28x1x7x7x1x320x1x3x3x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x29x29x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x32x32x1x1x1x1x1280x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x1280x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x32x32x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x32x32x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x1536x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x32x32x1x1x1x1x320x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x320x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x320x32x32x1x1x1x1x640x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x32x32x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x32x32x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x32x32x1x3x3x1x320x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x32x32x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x32x32x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x32x32x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x32x32x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x32x32x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x32x32x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x32x32x1x3x3x1x4x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x32x32x1x3x3x1x4x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x32x32x1x3x3x1x640x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x3x3x1x640x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x32x32x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x32x32x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x320x33x33x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10]
2x320x33x33x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x33x33x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x320x33x33x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x33x33x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x33x33x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x33x33x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x33x33x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x33x33x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x33x33x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x33x33x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x33x33x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x320x33x33x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x33x33x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x33x33x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x320x33x33x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x33x33x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x33x33x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x34x34x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10]
2x320x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x320x34x34x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x34x34x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x34x34x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x34x34x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x34x34x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x320x34x34x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x34x34x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x34x34x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x320x34x34x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x320x34x34x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x34x34x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x34x34x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x34x34x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x34x34x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x34x34x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x320x40x40x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x40x40x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x40x40x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x4x1024x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x4x1024x1x1x1x1x641x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x320x4x16384x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x4x196x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x4x4096x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x320x4x4x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x320x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x320x512x512x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x512x512x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x512x512x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x512x512x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x320x56x56x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x56x56x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x56x56x1x5x5x1x320x4x2x2x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x64x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x64x64x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x64x64x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x64x64x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x64x64x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x320x64x64x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x64x64x1x1x1x1x6x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x1x1x1x768x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x64x64x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x64x64x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x64x64x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x64x64x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x64x64x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x64x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x64x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x1x5x1x320x1x0x2x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x64x64x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x64x64x1x3x3x1x320x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:188
2x320x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x64x64x1x3x3x1x320x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x320x64x64x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x64x64x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x64x64x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:74
2x320x64x64x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x320x64x64x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x64x64x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x320x64x64x1x3x3x1x4x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x320x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x320x64x64x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x320x64x64x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x64x64x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x320x64x64x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x64x64x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x320x64x64x1x5x5x1x320x1x2x2x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x64x64x1x7x7x1x640x1x3x3x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x67x67x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x67x67x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x67x67x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x67x67x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x67x67x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x67x67x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x67x67x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x67x67x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x67x67x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x68x68x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x68x68x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x68x68x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x68x68x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x68x68x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x68x68x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x68x68x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x68x68x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x68x68x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x69x69x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x69x69x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x69x69x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x69x69x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x69x69x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x69x69x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x69x69x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x320x69x69x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x69x69x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x320x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x1152x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x7x7x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x320x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x320x7x7x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x320x7x7x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x320x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x7x7x1x3x3x1x160x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x160x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x7x7x1x3x3x1x160x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x320x7x7x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+32
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x7x7x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x320x7x7x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x160x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x320x7x7x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x160x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x160x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x320x7x7x1x3x3x1x160x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x7x7x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x7x7x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x7x7x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x7x7x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x320x7x7x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x7x7x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x7x7x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x7x7x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x7x7x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x7x7x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x320x7x7x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x7x7x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x7x7x1x5x1x1x320x1x2x0x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x7x7x1x7x7x1x320x4x3x3x0x1x1x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x80x80x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x80x80x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,175[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x320x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x320x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x320x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x320x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x320x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x8x8x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x320x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x320x8x8x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,290[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x8x8x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x320x8x8x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x3x3x1x192x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x320x8x8x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x320x8x8x1x3x3x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x192x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x320x8x8x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x320x8x8x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x8x8x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x8x8x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x8x8x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x8x8x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x8x8x1x3x3x1x320x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x320x8x8x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x8x8x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x8x8x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x8x8x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x8x8x1x3x3x1x320x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x320x8x8x1x3x3x1x320x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x96x96x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x320x96x96x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x320x96x96x1x3x3x1x4x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,1,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,161[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x320x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x9x9x1x3x3x1x192x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x320x9x9x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x9x9x1x3x3x1x192x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x192x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x192x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x320x9x9x1x3x3x1x192x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x320x9x9x1x3x3x1x320x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x320x9x9x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x320x9x9x1x3x3x1x320x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x320x9x9x1x3x3x1x320x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x9x9x1x3x3x1x320x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x320x9x9x1x3x3x1x320x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[6];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+64
2x324x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x324x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,6,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x324x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x324x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x324x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x324x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x324x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x324x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x324x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x324x512x512x1x3x3x1x324x1x1x1x0x1x1x0x1x1x0x0x324xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x324x512x512x1x3x3x1x324x4x1x1x0x1x1x0x1x1x0x0x324xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x324x56x56x1x1x1x1x77x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x324x64x64x1x1x1x1x1944x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x328x112x112x1x3x3x1x328x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x328x32x32x1x1x1x1x1968x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x328x32x32x1x1x1x1x2152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x328x512x512x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x328x56x56x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x328x56x56x1x3x3x1x328x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x328x64x64x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x328x64x64x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x328x7x7x1x1x1x1x2152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3296x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x1024x1024x1x1x1x1x10x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x1024x1024x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x1024x1024x1x1x1x1x24x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,132;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x1024x1024x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x1x1x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x32x1024x1024x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x32x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x32x1024x1024x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x1024x1024x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x1024x1024x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21
2x32x1024x1024x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x1025x1025x1x2x2x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x109x109x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x10x10x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x144x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x168x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,171;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,99;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x112x112x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x112x112x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x32x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x32x112x112x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x32x112x112x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+-1
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+-1
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x112x112x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x112x112x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x112x112x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x112x112x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x112x112x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x113x113x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x1184x1184x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x32x120x120x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x125x125x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x128x128x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x128x128x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x128x128x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x128x128x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x128x128x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x32x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x128x128x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,171;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x2x2x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x128x128x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x128x128x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x128x128x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x128x128x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x128x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x128x128x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x128x128x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x128x128x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x128x128x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x128x128x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x128x256x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x128x256x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x128x256x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x12x120x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x12x120x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x12x120x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x12x120x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x12x120x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x12x120x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x12x120x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x12x120x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x12x120x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x12x120x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x12x120x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x130x130x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,99;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x130x130x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,123[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x145x145x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,123[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10]
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x147x147x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x147x147x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x147x147x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x147x147x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x147x147x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x147x147x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x147x147x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x147x147x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x147x147x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x147x147x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x147x147x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x147x147x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x147x147x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x147x147x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x148x148x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x148x148x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x148x148x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x148x148x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x32x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x149x149x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x149x149x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,123[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x149x149x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x149x149x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x149x149x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x149x149x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x149x149x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x32x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x32x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x32x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x32x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x14x14x1x1x1x1x528x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x32x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x528x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x32x14x14x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,29[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x32x14x14x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x14x14x1x1x1x1x528x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x32x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,171;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,69;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x14x14x1x3x3x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,69;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x2x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,93[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+16
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x32x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,69;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x14x14x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x14x14x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x14x14x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x128x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x32x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x14x14x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x14x14x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x14x14x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x14x14x1x5x5x1x64x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x14x14x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x150x150x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x150x150x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x150x150x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x1536x1536x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209
2x32x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x32x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x32x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209
2x32x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x32x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x32x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x32x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x153x662x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x153x662x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x153x662x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x153x662x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x157x681x1x5x20x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x157x681x1x5x20x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x157x681x1x5x20x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x161x699x1x5x20x1x1x128x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x128x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x16x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x16x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x1x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x1x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x256x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x2x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x2x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x32x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x32x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x4x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x4x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x64x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x64x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x161x699x1x5x20x1x1x8x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x161x699x1x5x20x1x1x8x2x9x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x1668x1668x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x1668x1668x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1668x1668x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1668x1668x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1669x1669x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1669x1669x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1669x1669x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x1669x1669x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x16x16x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x16x16x1x3x3x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x16x16x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x16x16x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x16x16x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x16x16x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x32x16x16x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x16x16x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x16x16x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x32x16x16x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x192x128x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x192x128x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x3x3x1x49x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x192x128x1x3x3x1x49x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x192x128x1x3x3x1x49x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x1x1x1x1x1x1x390x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x1x1x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x1x1x1x1x1x1x520x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x1x1x1x1x1x1x720x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209
2x32x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x32x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x32x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209
2x32x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x32x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x32x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x32x208x208x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x224x224x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x2368x2368x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x24x240x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x24x240x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x24x240x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x240x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x24x24x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x24x24x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x32x253x253x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x32x256x256x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x32x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x256x256x1x2x2x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x256x256x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x256x256x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x256x256x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x256x256x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x256x256x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x256x256x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x257x257x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x25x25x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x25x25x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x25x25x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x264x264x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x26x26x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x26x26x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x32x27x27x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x27x27x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,139[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[6];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,10,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,29[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[10];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x32x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x2x2x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x2x2x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[8];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x28x28x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+8
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x32x28x28x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x32x28x28x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x32x28x28x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x32x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x32x28x28x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x32x28x28x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x28x28x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x28x28x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x28x28x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,69;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x28x28x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x32x28x28x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x32x28x28x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x32x28x28x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x32x28x28x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x32x28x28x1x5x5x1x16x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x32x28x28x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x28x28x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x28x28x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x32x28x28x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x32x28x28x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x32x28x28x1x5x5x1x16x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x32x28x28x1x5x5x1x16x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x32x28x28x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x28x28x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x28x28x1x5x5x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x32x28x28x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[7];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x28x28x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x28x28x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x28x28x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x28x28x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x28x28x1x5x5x1x96x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x5x5x1x96x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x5x5x1x96x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x28x28x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x28x28x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x5x5x1x96x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x5x5x1x96x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x5x5x1x96x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x5x5x1x96x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x28x28x1x5x5x1x96x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x28x28x1x5x5x1x96x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x5x5x1x96x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x28x28x1x7x7x1x32x1x9x9x0x1x1x0x3x3x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x295x295x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x295x295x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7]
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x295x295x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x295x295x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x295x295x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x297x297x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x297x297x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x297x297x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x297x297x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x297x297x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x299x299x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x299x299x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7]
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x299x299x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x299x299x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x299x299x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x2x2x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x2x2x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,99;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x2x2x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x2x2x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x32x2x2x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x2x2x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x32x2x2x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x32x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x32x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x32x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x32x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x32x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x32x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39
2x32x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x32x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x32x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x32x30x30x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x30x30x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x30x30x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x30x30x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x30x30x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x30x30x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x30x30x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x30x30x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x30x30x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x32x30x30x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x30x30x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x30x30x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x30x30x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x30x30x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x30x30x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x30x30x1x3x3x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x32x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x32x32x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x32x32x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x32x32x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x32x32x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x32x32x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x32x32x1x3x3x1x3x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x32x32x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x32x32x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x32x32x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x32x32x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x32x32x32x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x32x32x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x32x32x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x32x32x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x32x32x32x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x32x32x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,1,1,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,82[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x32x32x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x32x32x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x32x32x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x32x32x32x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x32x32x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x32x32x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x32x32x32x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x32x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[6];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x32x36x162x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[10]
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x36x162x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x38x166x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9]
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+128
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x38x166x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x38x166x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x32x40x170x1x5x10x1x32x1024x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x1024x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[10]
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x40x170x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x40x170x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x512x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x512x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+128
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x40x170x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x40x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x40x60x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x40x60x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x415x415x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x416x416x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x416x416x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x416x416x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x416x416x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x416x416x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x416x416x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x417x417x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x448x448x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x448x448x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x448x448x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x448x448x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x448x448x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x448x448x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x448x448x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x448x448x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x448x448x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x448x448x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x448x448x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x448x448x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7]
2x32x449x449x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x449x449x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x449x449x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x449x449x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x449x449x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x449x449x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x449x449x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x449x449x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x450x450x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x450x450x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x450x450x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x450x450x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x469x724x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x469x724x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x469x724x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x469x724x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x469x724x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x469x724x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x469x724x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x469x724x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x469x724x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x469x724x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x470x725x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x470x725x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x470x725x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x470x725x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x4x4x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x4x4x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x32x4x4x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x4x4x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x32x4x4x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x32x4x4x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x32x512x512x1x1x1x1x144x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x168x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x232x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x46x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x32x512x512x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x72x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x2x2x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x128x4x2x2x0x2x2x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x32x512x512x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x512x512x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x512x512x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x32x512x512x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x512x512x1x3x3x1x64x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x64x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x512x512x1x5x5x1x32x1x2x2x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x512x512x1x5x5x1x32x4x2x2x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x512x512x1x7x7x1x32x4x3x3x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x513x513x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x54x54x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x54x54x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x54x54x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x54x54x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x54x54x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x54x54x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x54x54x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x54x54x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x54x54x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x32x56x56x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[8];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x56x56x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x56x56x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x32x56x56x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x64x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x56x56x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x32x56x56x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x32x597x597x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9]
2x32x597x597x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x597x597x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x597x597x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x597x597x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x32x597x597x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x597x597x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x597x597x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x597x597x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9]
2x32x597x597x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x597x597x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x597x597x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x597x597x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x598x598x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x32x598x598x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x32x598x598x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x598x598x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x598x598x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x32x598x598x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x598x598x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x598x598x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x598x598x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x32x598x598x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x32x598x598x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x598x598x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x32x598x598x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x60x60x1x3x3x1x64x1x0x0x0x3x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x32x64x128x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x64x64x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x64x64x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x64x64x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x64x64x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x64x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x64x64x1x3x3x1x4x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,93[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x64x64x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,61;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x64x64x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x64x64x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x64x64x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x32x64x64x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x64x64x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x32x65x65x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x32x71x323x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x32x71x323x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x32x71x323x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[7];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x71x323x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x32x71x323x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x75x332x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+32
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x75x332x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x75x332x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x75x332x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x75x332x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x75x332x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x75x332x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x75x75x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x76x332x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x76x332x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x76x332x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x76x332x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x76x332x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x76x332x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x76x332x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x76x332x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x76x332x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x76x332x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x76x332x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x77x332x1x5x20x1x1x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x77x332x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x77x332x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x340x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x340x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x340x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x340x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x340x1x5x10x1x32x128x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x79x340x1x5x10x1x32x128x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x16x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x79x340x1x5x10x1x32x16x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x1x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x79x340x1x5x10x1x32x1x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x79x340x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x340x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x340x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x340x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x79x340x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x79x340x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x2x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x79x340x1x5x10x1x32x2x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x79x340x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x340x1x5x10x1x32x32x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x32x79x340x1x5x10x1x32x32x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[9];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x4x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x79x340x1x5x10x1x32x4x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x340x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x340x1x5x10x1x32x64x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x79x340x1x5x10x1x32x64x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x340x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x340x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x340x1x5x10x1x32x8x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,132[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x79x340x1x5x10x1x32x8x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x32x79x341x1x5x10x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x341x1x5x10x1x32x1024x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, OddC, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x128x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x341x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x16x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x16x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x79x341x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x79x341x1x5x10x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x79x341x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x1x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x341x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x2x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x2x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x79x341x1x5x10x1x32x32x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x32x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x79x341x1x5x10x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x4x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x79x341x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x79x341x1x5x10x1x32x4x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x512x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, OddC, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x64x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x79x341x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x8x2x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x79x341x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x79x341x1x5x20x1x1x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x79x341x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x79x341x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x79x341x1x5x20x1x1x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x32x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x32x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x32x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x32x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x32x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x32x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x32x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x32x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x32x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[6];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x7x7x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x7x7x1x3x3x1x128x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x7x7x1x3x3x1x128x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[8];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x32x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x32x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x32x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x32x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x32x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x32x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x32x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x32x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x80x120x1x1x1x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x80x120x1x1x1x1x1x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x80x120x1x1x1x1x1x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x32x80x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x80x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x80x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x80x120x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x80x120x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x80x120x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x80x120x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x80x120x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x32x80x120x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x32x80x120x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x80x120x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x80x120x1x3x3x1x3x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x80x120x1x3x3x1x3x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x80x120x1x3x3x1x3x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x80x120x1x3x3x1x3x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x80x120x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x80x120x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x32x80x120x1x3x3x1x96x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x32x80x120x1x3x3x1x96x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
2x32x80x120x1x3x3x1x96x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x32x80x120x1x3x3x1x96x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x32x81x350x1x5x20x1x1x1024x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x1024x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x128x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x16x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x32x81x350x1x5x20x1x1x1x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x256x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x2x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x32x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x81x350x1x5x20x1x1x512x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x512x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x64x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x32x81x350x1x5x20x1x1x8x2x9x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x32x8x8x1x4x4x1x32x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x8x8x1x7x7x1x16x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x8x8x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x32x8x8x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x32x8x8x1x7x7x1x64x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x8x8x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x32x8x8x1x7x7x1x8x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x32x9x9x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3328x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x332x128x128x1x1x1x1x1328x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x332x1x1x1x1x1x1x166x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x332x256x256x1x3x3x1x332x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x332x64x64x1x3x3x1x332x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x11x11x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x336x11x11x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x336x128x128x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x128x128x1x1x1x1x888x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x336x128x128x1x1x1x1x888x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x336x128x128x1x3x3x1x336x1x1x1x0x1x1x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x336x128x128x1x5x5x1x336x4x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x14x14x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x336x14x14x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x336x14x14x1x5x5x1x336x1x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x336x14x14x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x336x14x14x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x336x14x14x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x336x14x14x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x14x14x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x336x1x1x1x1x1x1x14x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x336x1x1x1x1x1x1x14x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x1x1x1x1x1x1x14x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+1
2x336x1x1x1x1x1x1x14x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,5,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x336x1x1x1x1x1x1x14x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x1x1x1x1x1x1x14x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+1
2x336x1x1x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x21x21x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x336x21x21x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x336x21x21x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x336x21x21x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x21x21x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x336x21x21x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x336x21x21x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x336x21x21x1x3x3x1x336x64x1x1x0x1x1x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x21x21x1x3x3x1x336x64x1x1x0x1x1x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x21x21x1x3x3x1x336x64x1x1x0x1x1x0x1x1x0x0x336xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x336x21x21x1x5x5x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x21x21x1x5x5x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x336x21x21x1x5x5x1x336x64x2x2x0x1x1x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x21x21x1x5x5x1x336x64x2x2x0x1x1x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x21x21x1x5x5x1x336x64x2x2x0x1x1x0x1x1x0x0x336xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x336x21x21x1x7x7x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x21x21x1x7x7x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x336x21x21x1x7x7x1x336x64x3x3x0x1x1x0x1x1x0x0x336xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x336x21x21x1x7x7x1x336x64x3x3x0x1x1x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x21x21x1x7x7x1x336x64x3x3x0x1x1x0x1x1x0x0x336xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x336x223x223x1x1x1x1x576x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x336x223x223x1x1x1x1x576x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x336x224x224x1x1x1x1x576x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x336x224x224x1x1x1x1x576x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x336x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x256x256x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x336x256x256x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x256x256x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x336x256x256x1x3x3x1x336x1x1x1x0x2x2x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x259x259x1x5x5x1x336x1x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x259x259x1x5x5x1x336x4x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x336x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x336x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x336x28x28x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x336x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x336x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x336x28x28x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x28x28x1x5x5x1x336x16x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x28x28x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x28x28x1x5x5x1x336x32x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x336x28x28x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x28x28x1x5x5x1x336x64x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x29x29x1x3x3x1x336x4x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x31x31x1x5x5x1x336x1x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x31x31x1x5x5x1x336x4x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x32x32x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x32x32x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x32x32x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x32x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x42x42x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x336x42x42x1x1x1x1x1008x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x336x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x45x45x1x5x5x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x47x47x1x7x7x1x336x64x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x48x48x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x48x48x1x5x5x1x336x4x2x2x0x1x1x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x336x4x1024x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x4x4096x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x4x4096x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x4x4096x1x1x1x1x673x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x336x4x49x1x1x1x1x673x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x336x512x512x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x512x512x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x512x512x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x512x512x1x1x1x1x672x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x512x512x1x3x3x1x336x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x512x512x1x3x3x1x336x4x1x1x0x1x1x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x515x515x1x5x5x1x336x4x0x0x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x336x55x55x1x1x1x1x576x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x55x55x1x1x1x1x576x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x336x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x336x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x336x56x56x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x56x56x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x56x56x1x1x1x1x576x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x56x56x1x1x1x1x576x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x336x56x56x1x1x1x1x576x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x672x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x64x64x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x64x64x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x336x64x64x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x336x64x64x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x336x64x64x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x336x64x64x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x336x64x64x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x336x64x64x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x336x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x340x128x128x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x340x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:38
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:202;TransposedConvBinWinoRxS<3-2>:117
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Default, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+1
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:34
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:182;TransposedConvBinWinoRxS<3-2>:101
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:33
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:182;TransposedConvBinWinoRxS<3-2>:94
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:32
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:184;TransposedConvBinWinoRxS<3-2>:92
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[6];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:13
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:189;TransposedConvBinWinoRxS<3-2>:123
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,6,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[5];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:77
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1;TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:98
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:25
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:180
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,30;ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:11
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[7];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:188;TransposedConvBinWinoRxS<3-2>:143
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+64
2x340x1x1x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:14
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[8];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:191;TransposedConvBinWinoRxS<3-2>:136
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16;TransposedConvBinWinoRxS<3-2>:135
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:214;TransposedConvBinWinoRxS<3-2>:103
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x1x1x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:18
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1;TransposedConvBinWinoRxS<2-3>:178;TransposedConvBinWinoRxS<3-2>:100
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+32
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x340x1x1x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:20
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:187;TransposedConvBinWinoRxS<3-2>:96
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x1x1x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:250
2x340x38x38x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:255
2x340x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:256
2x340x38x38x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:247
2x340x38x38x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:256
2x340x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:179;TransposedConvBinWinoRxS<3-2>:89
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+-1
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:256
2x340x38x38x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+2
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:105
2x340x38x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];TransposedConvBinWinoRxS<2-3>:182;TransposedConvBinWinoRxS<3-2>:118
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+4
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:232
2x340x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:89
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:176
2x340x38x38x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:232;TransposedConvBinWinoRxS<3-2>:102
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+-1
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:256
2x340x38x38x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:237
2x340x38x38x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:88
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+2
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];TransposedConvBinWinoRxS<3-2>:251
2x340x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:88
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:32
2x340x3x3x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:181;TransposedConvBinWinoRxS<3-2>:94
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];TransposedConvBinWinoRxS<3-2>:44
2x340x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:218;TransposedConvBinWinoRxS<3-2>:109
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];TransposedConvBinWinoRxS<3-2>:34
2x340x3x3x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:98
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];TransposedConvBinWinoRxS<3-2>:34
2x340x3x3x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:89
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x340x3x3x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,290[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:16
2x340x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:179;TransposedConvBinWinoRxS<3-2>:111
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+2
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:76
2x340x3x3x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];TransposedConvBinWinoRxS<2-3>:187;TransposedConvBinWinoRxS<3-2>:88
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:10
2x340x3x3x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];TransposedConvBinWinoRxS<2-3>:191;TransposedConvBinWinoRxS<3-2>:196
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:19
2x340x3x3x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];TransposedConvBinWinoRxS<2-3>:190;TransposedConvBinWinoRxS<3-2>:89
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+64
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:13
2x340x3x3x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];TransposedConvBinWinoRxS<2-3>:182;TransposedConvBinWinoRxS<3-2>:93
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:128
2x340x3x3x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];TransposedConvBinWinoRxS<2-3>:180;TransposedConvBinWinoRxS<3-2>:96
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];TransposedConvBinWinoRxS<3-2>:20
2x340x3x3x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:189;TransposedConvBinWinoRxS<3-2>:93
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+32
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+16
2x340x3x3x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+16
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:52
2x340x3x3x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:183;TransposedConvBinWinoRxS<3-2>:89
2x344x128x128x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x344x17x17x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:206;TransposedConvBinWinoRxS<3-2>:94
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16;TransposedConvBinWinoRxS<3-2>:43
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2;TransposedConvBinWinoRxS<2-3>:179;TransposedConvBinWinoRxS<3-2>:89
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x344x1x1x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+32
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1;TransposedConvBinWinoRxS<2-3>:192;TransposedConvBinWinoRxS<3-2>:132
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32;TransposedConvBinWinoRxS<3-2>:16
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:184;TransposedConvBinWinoRxS<3-2>:114
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x344x1x1x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[9];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1;TransposedConvBinWinoRxS<2-3>:216;TransposedConvBinWinoRxS<3-2>:96
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+64;TransposedConvBinWinoRxS<3-2>:17
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:232;TransposedConvBinWinoRxS<3-2>:194
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:255
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];TransposedConvBinWinoRxS<3-2>:254
2x344x38x38x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:98
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];TransposedConvBinWinoRxS<3-2>:254
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:88
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];TransposedConvBinWinoRxS<3-2>:255
2x344x38x38x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];TransposedConvBinWinoRxS<2-3>:176;TransposedConvBinWinoRxS<3-2>:111
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:134
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];TransposedConvBinWinoRxS<2-3>:193;TransposedConvBinWinoRxS<3-2>:102
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];TransposedConvBinWinoRxS<3-2>:132
2x344x38x38x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:88
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];TransposedConvBinWinoRxS<3-2>:44
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:214;TransposedConvBinWinoRxS<3-2>:92
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];TransposedConvBinWinoRxS<3-2>:40
2x344x3x3x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];TransposedConvBinWinoRxS<2-3>:208;TransposedConvBinWinoRxS<3-2>:93
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:177;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:23
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:183;TransposedConvBinWinoRxS<3-2>:93
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];TransposedConvBinWinoRxS<3-2>:44
2x344x3x3x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;TransposedConvBinWinoRxS<2-3>:180;TransposedConvBinWinoRxS<3-2>:100
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+64
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:10
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];TransposedConvBinWinoRxS<2-3>:179;TransposedConvBinWinoRxS<3-2>:122
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];TransposedConvBinWinoRxS<3-2>:12
2x344x3x3x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;TransposedConvBinWinoRxS<2-3>:177;TransposedConvBinWinoRxS<3-2>:89
2x344x64x64x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x344x64x64x1x1x1x1x2064x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x3456x17x17x1x3x3x1x3456x1x1x1x0x1x1x0x1x1x0x0x3456xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x3456x17x17x1x3x3x1x3456x4x1x1x0x1x1x0x1x1x0x0x3456xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x3456x32x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3456x64x64x1x3x3x1x3456x4x1x1x0x1x1x0x1x1x0x0x3456xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x348x1x1x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x348x256x256x1x1x1x1x75x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x348x28x28x1x1x1x1x75x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x34x128x128x1x3x3x1x34x1x1x1x0x1x1x0x1x1x0x0x34xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x34x1x1x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x352x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x128x128x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x13x13x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x13x13x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x13x13x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x13x13x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x13x13x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x13x13x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x352x13x13x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x352x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x352x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x352x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x14x14x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x14x14x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x352x14x14x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x14x14x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x14x14x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x352x14x14x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x352x14x14x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x352x14x14x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x14x14x1x3x3x1x352x8x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x352x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x352x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x352x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x352x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x28x28x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x28x28x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x352x28x28x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x28x28x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x28x28x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x28x28x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x29x29x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x29x29x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x352x29x29x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x29x29x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x29x29x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x352x29x29x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x32x32x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x32x32x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x32x32x1x1x1x1x44x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x512x512x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x512x512x1x1x1x1x576x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x352x512x512x1x3x3x1x352x1x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x512x512x1x3x3x1x704x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x352x512x512x1x3x3x1x704x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x352x512x512x1x5x5x1x352x4x2x2x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x55x55x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x55x55x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x55x55x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x56x56x1x1x1x1x352x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x56x56x1x1x1x1x708x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,1,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,83[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x56x56x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x56x56x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x56x56x1x3x3x1x352x4x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x56x56x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x56x56x1x5x5x1x352x1x2x2x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x57x57x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x57x57x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x57x57x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x64x64x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x64x64x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x352x64x64x1x1x1x1x1984x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x352x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x64x64x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x352x64x64x1x3x3x1x352x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x64x64x1x3x3x1x352x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x128x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x32x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x6x6x1x3x3x1x352x64x0x0x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x1056x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x2112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x7x7x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x352x7x7x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x352x7x7x1x1x1x1x352x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x352x7x7x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x352x7x7x1x1x1x1x352x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x352x7x7x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x352x7x7x1x1x1x1x352x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x7x7x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x352x7x7x1x1x1x1x352x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x352x7x7x1x1x1x1x352x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x352x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x352x7x7x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x7x7x1x1x1x1x352x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x1x1x1x44x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x352x7x7x1x3x3x1x352x10x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x10x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x10x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x10x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x3x3x1x352x10x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x10x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x10x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x10x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x352x7x7x1x3x3x1x352x11x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x11x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x11x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x11x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x3x3x1x352x11x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x11x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x11x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x11x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x128x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x128x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x16x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x16x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x16x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x16x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x16x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x352x7x7x1x3x3x1x352x20x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x20x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x20x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x20x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x20x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x20x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x20x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x20x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x22x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x32x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x352x7x7x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x32x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x352x7x7x1x3x3x1x352x64x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x352x7x7x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x352x7x7x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x64x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x352x7x7x1x3x3x1x352x8x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x8x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x352x7x7x1x3x3x1x352x8x1x1x0x1x1x0x1x1x0x0x352xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x352x7x7x1x3x3x1x352x8x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x352x7x7x1x3x3x1x352x8x1x1x0x2x2x0x1x1x0x0x352xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x354x128x128x1x5x5x1x354x1x2x2x0x1x1x0x1x1x0x0x354xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x356x512x512x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x35x128x128x1x1x1x1x51x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x128x128x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x24x16x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x256x256x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x256x256x1x1x1x1x210x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x256x256x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x28x28x1x1x1x1x51x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x28x28x1x1x1x1x51x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x28x28x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x28x28x1x1x1x1x61x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x35x48x32x1x1x1x1x35x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x35x48x32x1x1x1x1x35x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x35x48x32x1x1x1x1x35x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x35x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x35x48x32x1x1x1x1x35x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x48x32x1x1x1x1x35x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x35x48x32x1x1x1x1x64x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x48x32x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x35x512x512x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x512x512x1x1x1x1x210x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x35x512x512x1x1x1x1x210x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x360x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x360x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x360x128x128x1x3x3x1x360x1x1x1x0x1x1x0x1x1x0x0x360xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x360x128x128x1x3x3x1x360x4x1x1x0x1x1x0x1x1x0x0x360xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x360x128x128x1x3x3x1x360x4x1x1x0x2x2x0x1x1x0x0x45xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x360x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x360x1x1x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x360x1x1x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x360x1x1x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x360x64x64x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x360x64x64x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x360x64x64x1x3x3x1x360x1x1x1x0x1x1x0x1x1x0x0x360xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x366x256x256x1x3x3x1x366x1x1x1x0x2x2x0x1x1x0x0x366xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x366x64x64x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x368x128x128x1x3x3x1x368x4x1x1x0x2x2x0x1x1x0x0x46xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x368x14x14x1x3x3x1x368x1x1x1x0x2x2x0x1x1x0x0x46xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x368x1x1x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x368x7x7x1x1x1x1x368x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x36x100x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x100x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x100x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x100x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x100x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x100x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x100x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x1024x1024x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x36x1024x1024x1x3x3x1x36x1x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x36x1024x1024x1x3x3x1x36x4x1x1x0x2x2x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x36x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x104x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x104x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x108x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x108x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x10x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x10x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x10x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x112x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x112x112x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x36x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x112x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x112x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x112x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x112x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x112x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x116x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x116x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x116x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x116x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x11x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x11x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x11x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x11x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x11x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x11x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x11x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x120x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x120x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x124x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x124x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x128x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x128x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x128x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x12x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x12x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x12x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x12x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x12x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x36x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x12x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x12x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x136x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x136x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x136x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x136x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x13x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x13x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x13x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x13x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x13x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x140x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x140x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x140x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x140x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x144x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x144x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x148x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x148x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x36x14x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x14x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x14x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x14x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x14x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x14x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x14x14x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x152x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x152x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x156x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x156x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x156x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x156x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x156x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x156x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x15x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x15x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x15x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x15x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x160x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x160x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x164x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x164x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x164x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x164x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x168x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x168x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x168x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x168x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x16x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x16x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x17x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x17x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x18x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x18x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x36x18x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x18x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x19x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x19x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x19x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x19x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x1x1x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x1x1x1x1x1x1x140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x1x1x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x20x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x20x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x20x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x20x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x20x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x20x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x20x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x20x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x20x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x20x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x20x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x20x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x20x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x21x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x21x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,2,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x21x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x22x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x22x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x22x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x22x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x22x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x22x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x22x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x22x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x22x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x22x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x22x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x22x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x23x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x36x23x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x23x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x23x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x23x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x24x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x24x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x24x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x24x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x24x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x24x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x256x256x1x1x1x1x18x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x36x256x256x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x256x256x1x3x3x1x36x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x36x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x25x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x25x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x36x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x25x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x25x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x26x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x26x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x27x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x27x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x28x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x28x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x28x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x28x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x28x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x28x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x28x28x1x3x3x1x72x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x29x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,2,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x29x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x30x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x30x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x30x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x30x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x30x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,21[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x30x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x30x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x30x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x31x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x31x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x31x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x31x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x32x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x32x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x32x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x32x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x33x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x33x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x34x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x34x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x36x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x36x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x36x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x36x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x36x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x36x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x36x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x36x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x37x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x37x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x37x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x37x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x37x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x37x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x37x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x37x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x36x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x36x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x40x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x40x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x40x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x40x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x36x40x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x40x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x40x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x40x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x40x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x40x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x41x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x41x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x41x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x41x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x36x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x36x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x42x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x42x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x42x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x44x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x44x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x44x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x44x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x44x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x44x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x44x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x44x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x44x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x46x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x46x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x46x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x46x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x46x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x46x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x36x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x48x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x48x52x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x52x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x48x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x48x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x48x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x36x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x48x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x48x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x50x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x50x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x50x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x50x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x36x50x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x50x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x50x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x50x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x512x512x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x52x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x52x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x52x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x52x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x52x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x52x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x56x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x56x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x56x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x56x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x56x56x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x36x56x56x1x1x1x1x36x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x36x56x56x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x36x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x36x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x58x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x58x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x58x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x58x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x5x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x5x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x60x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x60x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x60x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x60x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x60x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x60x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x60x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x60x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x62x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x62x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x62x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x64x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x64x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x36x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x64x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x64x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x64x64x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x36x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x68x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x68x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x36x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x68x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x68x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x68x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x68x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x68x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x68x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x6x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x6x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x6x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x70x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x70x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x36x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x36x70x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x70x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x70x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x70x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x70x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x70x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x70x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x70x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x72x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x72x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x74x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x74x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x36x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x76x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x76x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x76x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x76x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x36x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x78x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x78x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x7x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x36x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x80x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x36x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x80x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x80x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x80x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x80x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x80x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x80x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x82x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x82x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x82x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x82x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x82x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x82x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x84x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x84x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x84x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x36x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x84x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x36x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x88x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x88x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x8x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x8x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x36x92x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x92x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x92x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x36x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x36x96x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x36x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x36x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x96x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x36x96x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x36x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x36x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x36x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x36x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x36x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x36x9x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x36x9x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x370x7x7x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x3712x128x128x1x3x3x1x3712x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x3712x1x1x1x1x1x1x348x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x3712x64x64x1x3x3x1x3712x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x3712x7x7x1x1x1x1x3712x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x372x128x128x1x3x3x1x372x4x1x1x0x1x1x0x1x1x0x0x372xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x372x64x64x1x1x1x1x124x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x372x64x64x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x376x256x256x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x37x1x1x1x1x1x1x450x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x37x28x28x1x1x1x1x171x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3840x4x4x1x1x1x1x1280x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x3840x4x4x1x1x1x1x1280x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3840x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3840x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:61
2x3840x4x4x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x384x1024x2048x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x1024x2048x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x1024x2048x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x1024x4095x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x384x1024x4095x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x384x10x10x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x111x111x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x112x112x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x113x113x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x125x125x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x125x125x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x126x126x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x126x126x1x1x1x1x1088x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x1048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x1x1x1x1408x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x128x128x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x3x3x1x1408x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x3x3x1x1408x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x128x128x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x5x1x1x384x4x2x0x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x128x128x1x5x5x1x384x4x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x128x128x1x7x7x1x384x4x3x3x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x384x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x384x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x384x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x139x139x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x139x139x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x139x139x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x139x139x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x13x13x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x13x13x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x192x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x384x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[7];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x13x13x1x3x3x1x192x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x384x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x13x13x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x384x13x13x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x13x13x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x13x13x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x384x13x13x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x13x13x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x140x140x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x140x140x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x140x140x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x140x140x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x140x140x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x140x140x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x140x140x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x140x140x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x140x140x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x140x140x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x141x141x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x141x141x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x147x147x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x147x147x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x147x147x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x147x147x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x1048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x1048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x1096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1264x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1264x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x384x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x384x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x384x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x384x14x14x1x1x1x1x1336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x1432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x14x14x1x1x1x1x1456x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1456x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x14x14x1x1x1x1x1528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x14x14x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x384x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x771x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x14x14x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x384x14x14x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x2x2x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x2x2x1x768x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x2x2x1x768x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x2x2x1x768x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x2x2x1x768x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x2x2x1x768x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x14x14x1x2x2x1x768x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x14x14x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x384x14x14x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x11x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x11x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x384x14x14x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x384x14x14x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x21x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x21x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x22x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x22x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x384x14x14x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x352x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x384x14x14x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x464x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x384x14x14x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x14x14x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x384x14x14x1x3x3x1x384x98x1x1x0x1x1x0x1x1x0x0x384xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x384x98x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x16x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x384x14x14x1x5x5x1x384x1x2x2x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x32x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x14x14x1x5x5x1x384x64x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x384x14x14x1x7x7x1x384x4x3x3x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x15x15x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x15x15x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x15x15x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x384x15x15x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x16x16x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x16x16x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+2
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x16x16x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x16x16x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x16x16x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x16x16x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x16x16x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x384x16x16x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+2
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+2
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x16x16x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x16x16x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x16x16x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x384x16x16x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x16x16x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x384x4x0x0x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x16x16x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x16x16x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x16x16x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x16x16x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x16x16x1x7x7x1x384x1x3x3x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x17x17x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x17x17x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x384x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x384x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x17x17x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x384x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x17x17x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x384x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+16
2x384x17x17x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x17x17x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x17x17x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x17x17x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+2
2x384x17x17x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x384x17x17x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x17x17x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x17x17x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x17x17x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x17x17x1x3x3x1x288x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x17x17x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x17x17x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x17x17x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x17x17x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x17x17x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x17x17x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x17x17x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x17x17x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x17x17x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x17x17x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x18x18x1x1x1x1x2304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x18x18x1x3x3x1x288x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x18x18x1x3x3x1x288x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x18x18x1x3x3x1x288x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x384x18x18x1x3x3x1x288x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+8
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x18x18x1x3x3x1x288x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x18x18x1x3x3x1x288x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x18x18x1x3x3x1x288x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x18x18x1x3x3x1x288x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x18x18x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x18x18x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x18x18x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x18x18x1x3x3x1x384x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x18x18x1x3x3x1x384x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x18x18x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x19x19x1x1x1x1x2304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x1x1x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x1x21x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x1x21x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x1x21x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x1x21x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x1x21x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x1x21x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x1x21x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x1x21x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x1x21x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x1x21x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x2048x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x2048x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x2048x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x20x30x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x20x30x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x24x24x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x24x24x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x24x48x1x1x1x1x128x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x128x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x24x48x1x1x1x1x128x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x128x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x384x24x48x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x24x48x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x384x24x48x1x1x1x1x128x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x128x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x24x48x1x1x1x1x128x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x384x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x24x48x1x1x1x1x480x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x24x48x1x1x1x1x480x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x24x48x1x1x1x1x480x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x24x48x1x1x1x1x480x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x24x48x1x1x1x1x480x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x24x48x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x384x24x48x1x1x1x1x480x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x24x48x1x1x1x1x480x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x24x48x1x1x1x1x512x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x1x1x512x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x1x1x512x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x1x1x512x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x512x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x512x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x1x1x512x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x1x1x512x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x104x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x104x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x104x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x112x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x112x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x112x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x120x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x120x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x120x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x136x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x136x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x136x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x144x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x144x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x144x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x152x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x152x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x152x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x160x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x160x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x160x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x168x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x168x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x168x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x176x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x176x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x176x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x184x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x184x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x184x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x192x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x192x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x192x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x200x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x200x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x200x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x208x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x208x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x208x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x216x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x216x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x216x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x224x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x224x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x224x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x232x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x232x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x232x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x240x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x240x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x240x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x248x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x248x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x248x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x24x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x264x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x264x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x264x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x272x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x272x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x272x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x280x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x280x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x280x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x288x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x288x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x288x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x296x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x296x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x296x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x40x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x40x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x3x1x384x40x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x48x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x48x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x24x48x1x1x3x1x384x48x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x1x3x1x384x56x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x56x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x56x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x72x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x72x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x72x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x80x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x80x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x80x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x88x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x88x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x88x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x384x24x48x1x1x3x1x384x96x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x1x3x1x384x96x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x1x3x1x384x96x0x1x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x104x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x104x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x104x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x112x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x112x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x112x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x3x1x1x384x120x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x120x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x120x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x136x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x136x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x136x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x144x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x144x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x144x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x152x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x152x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x152x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x160x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x160x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x160x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x168x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x168x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x168x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x176x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x176x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x176x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x184x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x184x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x184x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x192x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x192x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x192x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x200x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x200x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x200x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x208x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x208x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x208x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x216x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x216x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x216x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x224x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x224x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x224x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x232x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x232x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x232x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x240x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x240x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x240x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x248x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x248x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x248x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x24x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x264x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x264x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x264x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x272x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x272x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x272x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x280x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x280x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x280x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x288x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x288x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x288x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x296x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x296x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x296x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x40x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x40x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x3x1x1x384x40x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x24x48x1x3x1x1x384x48x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x48x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x3x1x1x384x48x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x56x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x56x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x56x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x384x24x48x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x3x1x1x384x72x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x72x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x24x48x1x3x1x1x384x72x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x3x1x1x384x80x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x80x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x80x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x3x1x1x384x88x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x88x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x88x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x24x48x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x24x48x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x384x24x48x1x3x1x1x384x96x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x24x48x1x3x1x1x384x96x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x24x48x1x3x1x1x384x96x1x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x253x253x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x253x253x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x253x253x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x253x253x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x256x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x256x256x1x1x1x1x768x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x1x1x1x772x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x256x256x1x1x1x1x773x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x256x256x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x256x256x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x256x256x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x256x256x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x256x256x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x256x256x1x5x5x1x384x1x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x256x256x1x5x5x1x384x4x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x256x256x1x5x5x1x384x4x2x2x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x257x257x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x25x25x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x25x25x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x27x27x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x27x27x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x27x27x1x1x1x1x48x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x27x27x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x27x27x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x27x27x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x27x27x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x27x27x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x384x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x384x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x3072x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x28x28x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[6];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:149
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x384x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x28x28x1x1x1x1x772x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x2x2x1x768x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x28x28x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x28x28x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x28x28x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x28x28x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x28x28x1x5x5x1x384x4x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x28x28x1x5x5x1x384x4x2x2x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x28x28x1x7x7x1x384x1x3x3x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x29x29x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x2x2x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x30x30x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+64
2x384x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x31x31x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x31x31x1x3x3x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x384x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x32x32x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x32x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x32x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x32x32x1x3x3x1x4x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x32x32x1x5x5x1x384x1x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+64
2x384x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x33x33x1x3x3x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x33x33x1x3x3x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x33x33x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x33x33x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x33x33x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x33x33x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x33x33x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x33x33x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x33x33x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x33x33x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x34x34x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x34x34x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x34x34x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x34x34x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x34x34x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x34x34x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x34x34x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x34x34x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x34x34x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x34x34x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x384x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x35x35x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x384x35x35x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x35x35x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x35x35x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x35x35x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x35x35x1x3x3x1x288x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x384x35x35x1x3x3x1x288x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x35x35x1x3x3x1x288x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x384x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x384x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x384x35x35x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x37x37x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x384x48x32x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x48x32x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x384x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x384x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x384x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x384x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x48x32x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x384x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x384x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x419x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x384x48x32x1x1x1x1x419x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x384x48x32x1x1x1x1x419x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x384x48x32x1x1x1x1x419x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x419x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x419x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x48x32x1x1x1x1x419x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x48x32x1x1x1x1x419x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x48x32x1x1x1x1x419x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x384x48x32x1x1x1x1x419x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x384x48x32x1x1x1x1x419x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x419x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x384x48x32x1x1x1x1x419x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x384x48x32x1x1x1x1x419x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x48x32x1x1x1x1x419x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,195[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x384x48x32x1x1x1x1x448x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x384x48x32x1x1x1x1x448x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x384x48x32x1x1x1x1x448x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x384x48x32x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x448x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x448x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x448x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x48x32x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x384x48x32x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x384x48x32x1x1x1x1x448x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x48x32x1x1x1x1x448x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x48x32x1x1x1x1x96x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x96x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x96x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x96x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x48x32x1x1x1x1x96x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x1x1x1x96x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x104x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x104x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x104x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x112x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x112x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x112x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x120x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x120x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x120x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x48x32x1x3x3x1x384x136x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x136x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x136x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x144x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x144x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x144x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x152x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x152x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x152x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x160x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x160x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x160x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x168x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x168x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x168x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x48x32x1x3x3x1x384x176x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x176x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x176x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x184x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x184x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x184x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x48x32x1x3x3x1x384x192x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x192x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x192x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x200x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x200x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x200x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x48x32x1x3x3x1x384x208x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x208x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x208x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x216x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x216x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x216x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x224x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x224x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x224x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x232x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x232x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x232x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x240x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x240x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x240x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x248x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x248x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x248x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x384x48x32x1x3x3x1x384x24x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x24x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x24x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x48x32x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x264x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x264x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x264x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x272x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x272x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x272x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x280x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x280x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x280x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x288x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x288x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x288x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x296x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x296x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x296x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x384x48x32x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x48x32x1x3x3x1x384x40x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x40x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x40x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x48x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x48x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x48x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x56x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x56x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x56x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x384x48x32x1x3x3x1x384x72x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x72x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x72x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x80x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x80x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x80x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x88x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x48x32x1x3x3x1x384x88x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x88x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x32x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x48x32x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x48x32x1x3x3x1x384x96x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x48x32x1x3x3x1x384x96x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x48x32x1x3x3x1x384x96x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x48x48x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x4x1024x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x4x1024x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x4x16x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x16x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x4x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x256x1x1x1x1x769x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x4x4096x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x4x4096x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x4x4096x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x4x49x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x4x49x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x4x49x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x49x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x4x49x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x4x4x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x4x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x4x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x384x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x4x4x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x4x4x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x4x4x1x3x3x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x4x4x1x3x3x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x4x4x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x384x4x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x4x64x1x1x1x1x769x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x4x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x4x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x512x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x384x512x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x512x1024x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244
2x384x512x512x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x512x512x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x512x512x1x2x2x1x768x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x512x512x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x512x512x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x512x512x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x512x512x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x512x512x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x56x56x1x2x2x1x768x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x56x56x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x384x56x56x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x56x56x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x56x56x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x56x56x1x3x3x1x768x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x57x57x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x384x57x57x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x62x62x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x384x62x62x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x62x62x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x64x64x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x64x64x1x1x1x1x1408x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x384x64x64x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x64x64x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x12xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x64x64x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x64x64x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x64x64x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x64x64x1x3x3x1x384x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x64x64x1x5x5x1x384x1x2x2x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x64x64x1x9x9x1x384x1x4x4x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x69x69x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x384x69x69x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x384x69x69x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x384x69x69x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x384x69x69x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x384x69x69x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x69x69x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3]
2x384x69x69x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x69x69x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x69x69x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x69x69x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x69x69x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x384x69x69x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x384x69x69x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x69x69x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x69x69x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x6x6x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x6x6x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x6x6x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x6x6x1x3x3x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x6x6x1x3x3x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x6x6x1x3x3x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x6x8x1x3x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x6x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x6x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x6x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x6x8x1x3x3x1x448x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x70x70x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x384x70x70x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x288x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x384x70x70x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x70x70x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x384x70x70x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x384x70x70x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x70x70x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3]
2x384x70x70x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x288x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x70x70x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x70x70x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x70x70x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x384x70x70x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x384x70x70x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x384x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x384x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x384x70x70x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x70x70x1x3x3x1x384x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x70x70x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x70x70x1x3x3x1x384x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x384x74x74x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x768x1536x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x768x1536x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x768x1536x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x384x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x384x7x7x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x384x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x384x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,3,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x384x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x7x7x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x7x7x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x384x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+32
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x384x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x7x7x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x384x7x7x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x384x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x384x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x7x7x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x1024x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x128x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x7x7x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x256x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x352x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x384x7x7x1x3x3x1x384x464x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x384x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x7x7x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x384x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x384x7x7x1x5x5x1x384x4x2x2x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x8x4x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x8x4x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x4x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x8x4x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x6x1x3x3x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x6x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x6x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x6x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x6x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x6x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x6x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x384x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x384x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x1x1x1536x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x384x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x384x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x256x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x256x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x256x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x256x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x384x1024x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x384x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x1x3x1x384x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x3x1x384x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x1x3x1x448x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x448x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x448x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x448x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x448x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x448x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x448x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x448x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x448x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x1x3x1x448x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x8x8x1x1x3x1x448x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x384x8x8x1x1x3x1x448x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x1x3x1x448x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x1x3x1x448x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x1x3x1x448x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x1x3x1x448x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x256x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x256x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x384x1024x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x1x1x384x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x8x8x1x3x1x1x384x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x384x8x8x1x3x1x1x384x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x1x1x384x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x384x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x384x8x8x1x3x1x1x384x84x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x3x1x1x384x86x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x3x1x1x384x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x384x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x3x1x1536x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x8x8x1x3x3x1x1536x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x8x8x1x3x3x1x1536x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x3x1x1536x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x384x8x8x1x3x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x3x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x8x8x1x3x3x1x384x256x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x3x1x384x256x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x384x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x384x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x3x1x384x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x384x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x384x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x3x3x1x448x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x384x8x8x1x3x3x1x448x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x8x8x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x384x8x8x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x3x3x1x448x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x384x8x8x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x384x8x8x1x3x3x1x448x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x384x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x384x8x8x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x384x8x8x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x3x1x448x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x384x8x8x1x3x3x1x448x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x384x8x8x1x3x3x1x448x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x384x8x8x1x3x3x1x448x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x384x8x8x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x384x8x8x1x3x3x1x448x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x384x8x8x1x3x3x1x448x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x384x8x8x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x384x8x8x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x384x8x8x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x384x96x96x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x384xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x384x96x96x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x384x9x9x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x386x14x14x1x1x1x1x2316x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x38x1024x1024x1x3x3x1x38x1x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x38x112x112x1x3x3x1x38x1x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x38x1x1x1x1x1x1x462x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x38x56x56x1x1x1x1x228x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x38x7x7x1x3x3x1x38x4x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x390x256x256x1x1x1x1x79x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x390x28x28x1x1x1x1x79x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x390x28x28x1x3x3x1x390x1x1x1x0x1x1x0x1x1x0x0x390xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x392x128x128x1x1x1x1x784x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x392x256x256x1x1x1x1x784x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x396x32x32x1x5x5x1x396x1x2x2x0x1x1x0x1x1x0x0x396xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x396x64x64x1x3x3x1x396x1x1x1x0x1x1x0x1x1x0x0x396xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x396x64x64x1x3x3x1x396x4x1x1x0x1x1x0x1x1x0x0x396xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x396x64x64x1x5x5x1x396x4x2x2x0x1x1x0x1x1x0x0x396xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x396x64x64x1x7x7x1x396x1x3x3x0x1x1x0x1x1x0x0x396xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x399x128x128x1x5x5x1x399x4x2x2x0x1x1x0x1x1x0x0x399xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x399x14x14x1x5x5x1x399x1x2x2x0x1x1x0x1x1x0x0x399xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x399x1x1x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x399x1x1x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x399x64x64x1x5x5x1x399x1x2x2x0x1x1x0x1x1x0x0x399xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3x100x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x100x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x100x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x100x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x100x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x100x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x100x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x100x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x1023x1023x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x1023x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x1023x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1023x1023x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x1023x1x7x7x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x1023x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x2047x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1023x2047x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x1023x2047x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1023x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x16x16x1x384x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20
2x3x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34
2x3x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x3x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x3x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44
2x3x1024x1024x1x3x3x1x42x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x3x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x3x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34
2x3x1024x1024x1x3x3x1x8x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x4x4x1x352x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x7x7x1x128x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x7x7x1x256x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x1024x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x1024x2048x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1024x736x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x1029x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x2053x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1029x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1030x1030x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x104x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x104x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x1055x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1055x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1055x735x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1056x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1056x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1056x704x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1056x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1056x736x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1061x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1061x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1061x741x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x107x107x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x107x107x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x1087x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1087x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1087x799x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x704x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x800x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1088x800x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x108x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x108x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x108x108x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x108x108x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x108x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x108x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x108x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x108x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x1093x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1093x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1093x805x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x109x109x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x109x109x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x10x10x1x2x2x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,7,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x10x10x1x3x3x1x5x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x10x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x10x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x10x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x10x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x10x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x10x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x10x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x10x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x10x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x10x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x10x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x10x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x1119x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1119x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1119x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1120x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1120x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1120x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1120x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1120x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1125x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1125x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1125x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x112x112x1x7x7x1x256x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x112x112x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x112x112x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x1151x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1151x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1152x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1152x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1152x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1152x736x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1152x768x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1157x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1157x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x116x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x116x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x116x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x116x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x1183x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1183x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1183x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1184x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1184x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1184x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1184x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1184x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1189x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1189x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1189x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1195x1195x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1196x1196x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1197x1197x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1199x1199x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1199x1199x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1199x1199x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1199x1199x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x11x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x11x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x11x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x11x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x11x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x11x15x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x11x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x11x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x11x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x11x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x11x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x11x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x11x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x11x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x1200x1200x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1200x1200x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1205x1205x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x120x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x120x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x120x120x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x120x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x120x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x120x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x120x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x120x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x120x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x1215x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1215x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1216x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1216x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1216x768x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1216x800x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1221x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1221x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1247x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1247x735x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1248x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1248x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1248x736x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1248x736x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x124x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x124x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x124x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x124x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x1253x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1253x741x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1279x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1279x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1280x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1280x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1280x704x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1280x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1280x960x1x4x4x1x128x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x1285x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1285x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x128x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x128x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x128x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x128x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x12x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x12x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x12x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x12x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x12x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x12x17x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x12x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x12x18x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x12x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x12x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x12x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x12x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x1311x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1311x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1312x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1312x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1312x704x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1312x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1317x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1317x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1324x1324x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x1325x1325x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x132x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x132x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x132x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x132x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x132x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x132x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x1343x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1343x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1344x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1344x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1344x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1349x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x1349x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x136x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x136x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x136x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x136x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x136x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x136x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x136x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x136x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x136x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x136x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x13x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x13x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x13x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x13x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x13x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x13x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x13x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x140x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x140x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x140x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x140x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x140x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x140x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x144x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x144x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x144x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x144x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x144x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x144x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x148x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x148x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x148x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x148x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x148x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x148x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x148x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x148x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x14x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x14x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x14x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x14x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x14x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x14x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[9];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x152x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x152x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x152x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x152x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4
2x3x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x3x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x3x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44
2x3x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x3x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x3x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4
2x3x156x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x156x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x156x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x156x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x15x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x15x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x160x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x160x160x1x16x16x1x96x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x160x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x160x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x164x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x164x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x168x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x168x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x16x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x16x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x16x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x16x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x16x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x16x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x17x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x17x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[5];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x17x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x17x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x17x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x17x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x18x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x18x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x192x192x1x4x4x1x128x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x196x196x1x14x14x1x1024x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x19x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x19x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[8];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x19x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x19x19x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x1x1x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x1x1x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x3x1x1x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x1x1x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x1x1x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x3x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x2048x2048x1x14x14x1x768x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x1x1x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4
2x3x2048x2048x1x3x3x1x12x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2048x2048x1x3x3x1x20x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2048x2048x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x3x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x3x2048x2048x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x3x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x3x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44
2x3x2048x2048x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x56x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x3x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x3x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4
2x3x2048x2048x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x192x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x192x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x256x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x40x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x48x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x48x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x4x4x1x80x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x5x5x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x6x6x1x32x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x6x6x1x32x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x6x6x1x48x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x128x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x256x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x256x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x32x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x7x7x1x96x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2048x2048x1x9x9x1x48x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x2049x2049x1x3x3x1x24x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2049x2049x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2049x2049x1x3x3x1x72x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x2051x2051x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x2051x2051x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x2052x2052x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x2052x2052x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x2053x2053x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2053x2053x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x2058x2058x1x14x14x1x1024x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x20x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x20x12x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x20x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x20x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x20x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x20x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x20x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x20x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x20x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x20x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x20x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x20x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x217x217x1x11x11x1x96x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x217x217x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x11x11x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x218x218x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x218x218x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x219x219x1x11x11x1x64x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x96x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x219x219x1x11x11x1x96x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x21x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x11x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x3x21x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x21x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x21x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x21x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x21x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x21x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x21x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x220x220x1x11x11x1x64x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x220x220x1x11x11x1x64x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x96x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x220x220x1x11x11x1x96x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x221x221x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x221x221x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x221x221x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x221x221x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x221x221x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x222x222x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x222x222x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x222x222x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x222x222x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x224x224x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x11x11x1x64x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x16x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x30x0x0x0x14x14x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x30x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x6x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x8x0x0x0x14x14x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1024x8x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1280x16x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x1536x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x2048x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x2048x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x3072x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x3584x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x384x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x14x14x1x768x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x16x16x1x144x1x0x0x0x8x8x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x16x16x1x32x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x16x16x1x768x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x16x16x1x768x32x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x16x16x1x768x64x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x1x1x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x1x1x1x80x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x32x32x1x1024x1x0x0x0x32x32x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x10x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x16x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x16x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x16x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x40x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x40x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x40x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x40x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x40x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x56x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,227[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,136[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x3x224x224x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x3x224x224x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10]
2x3x224x224x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,7,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[7];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x3x224x224x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,9,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10]
2x3x224x224x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,32,256,32,16,64,4,1,1,1,2,0,1,6,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,228[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,135[4];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x3x224x224x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x76x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x4x4x1x10x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x4x4x1x128x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x128x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x152x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x352x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x64x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x80x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x4x4x1x96x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x5x5x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x6x6x1x32x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x112x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x128x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x128x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x144x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x192x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x256x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x352x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x11x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x3x224x224x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x3x224x224x1x7x7x1x64x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x3x224x224x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x3x224x224x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x3x224x224x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x21x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x22x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x3x224x224x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x3x224x224x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x3x224x224x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x3x224x224x1x7x7x1x64x352x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x352x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x464x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x464x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x64x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x3x224x224x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x3x224x224x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x3x224x224x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x3x224x224x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x3x224x224x1x7x7x1x64x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x768x4x0x0x0x7x7x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x224x224x1x7x7x1x96x98x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x98x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x8x8x1x384x4x0x0x0x8x8x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x8x8x1x768x4x0x0x0x8x8x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x1x1x1x3x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x1x1x1x3x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x16x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x3x3x1x56x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x3x3x1x72x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x225x225x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x2x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x64x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x11x11x1x96x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x11x11x1x96x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x227x227x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x7x7x1x64x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x227x227x1x7x7x1x64x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x227x227x1x7x7x1x64x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x227x227x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x228x228x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x228x228x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x228x228x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x228x228x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x228x228x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x228x228x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x228x228x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x229x229x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x229x229x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x229x229x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x22x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x3x22x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x22x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x22x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x22x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x22x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x230x230x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x230x230x1x7x7x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x230x230x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x233x233x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x233x233x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x233x233x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x233x233x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x233x233x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x23x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x23x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x23x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x23x23x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x23x23x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x23x23x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x23x23x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x23x23x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x23x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x3x23x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x23x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x23x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x23x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x23x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x240x240x1x12x12x1x192x1x0x0x0x12x12x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x240x240x1x12x12x1x384x1x0x0x0x12x12x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x240x240x1x16x16x1x768x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x24x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x24x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x24x24x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x24x24x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x24x24x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x24x24x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x24x24x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x24x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x24x26x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x24x30x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x24x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x24x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x3x24x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x38x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x24x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x24x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x2559x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x3071x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x3327x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x3711x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x4479x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x4735x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x4863x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x4991x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2559x5119x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x3072x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x3328x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x3712x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x4480x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x4736x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x4864x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x4992x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2560x5120x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x3077x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x3333x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x3717x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x2565x4485x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x4741x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x4869x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x4997x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2565x5125x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x256x256x1x16x16x1x640x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x16x16x1x768x2x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x16x16x1x768x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x16x16x1x896x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x32x32x1x768x4x0x0x0x32x32x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x3x256x256x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x256x256x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x256x256x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x256x256x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x256x256x1x8x8x1x192x1x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x256x256x1x8x8x1x192x28x0x0x0x8x8x0x1x1x0x0x3xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x258x258x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x258x258x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x258x258x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x25x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x25x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x25x25x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x25x25x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x25x25x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x25x25x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x25x25x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x25x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x25x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x31x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x25x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x33x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x34x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x25x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x37x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x39x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x25x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x25x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x25x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x261x261x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x2687x3327x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2688x3328x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2688x4992x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2693x3333x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2693x4997x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x26x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x26x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x26x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x26x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x26x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x26x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x27x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x27x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x27x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x27x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x27x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x27x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x27x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x27x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x2815x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2815x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2816x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2816x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2821x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2821x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x28x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x28x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x28x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x28x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x28x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x28x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x28x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x28x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x28x28x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2943x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2943x3455x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2944x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2944x3456x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2949x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x2949x3461x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x297x297x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x297x297x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x297x297x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x297x297x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x298x298x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x298x298x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x298x298x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x298x298x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x299x299x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x299x299x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x29x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x29x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x29x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x29x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x29x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x29x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x2x2x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x2x2x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x2x2x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x2x2x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x2x2x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x2x2x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x2x2x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x2x2x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x3x2x2x1x3x3x1x4x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x2x2x1x3x3x1x4x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x2x2x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x2x2x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x2x2x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x2x2x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x300x300x1x7x7x1x64x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x300x300x1x7x7x1x64x112x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x3x300x300x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x300x300x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x19x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x19x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x200x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x200x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x3x300x300x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:157
2x3x300x300x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x3x300x300x1x7x7x1x64x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:237
2x3x300x300x1x7x7x1x64x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:215
2x3x300x300x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x3x300x300x1x7x7x1x64x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x3x300x300x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x58x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x58x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x59x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x59x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x300x300x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:255
2x3x300x300x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x305x305x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x305x305x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x305x305x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3071x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3071x2815x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3072x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3072x2816x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x3x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x3x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x3x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10
2x3x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x3x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x3x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x3077x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3077x2821x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x30x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x30x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x30x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x30x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x30x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x30x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x30x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x30x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x30x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x30x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x30x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x30x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x30x30x1x3x3x1x32x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x30x30x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x30x30x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x30x30x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x30x30x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x3199x4351x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3199x4863x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x31x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x31x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x31x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x31x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x31x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x31x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x31x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x31x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x31x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x31x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x31x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x31x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x3200x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3200x3456x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3200x4352x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3200x4864x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3205x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3205x3461x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3205x4357x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3205x4869x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x329x329x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x128x1x4x4x1x768x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x32x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x32x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x32x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x32x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x32x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x32x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x32x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x32x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x32x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,0[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x32x32x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x32x32x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x3x3x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x32x32x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x32x32x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x5x5x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x32x32x1x5x5x1x6x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x330x330x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x331x331x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x331x331x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3327x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3328x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3333x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x336x336x1x14x14x1x1024x16x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x336x336x1x14x14x1x1280x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x336x336x1x14x14x1x3072x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x336x336x1x14x14x1x8x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x33x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x33x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x33x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x33x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x33x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x33x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x33x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x33x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x33x33x1x3x3x1x8x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x34x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x34x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x34x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x34x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x34x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x34x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x34x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x34x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x34x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x34x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x3583x3199x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3584x3200x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3589x3205x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x35x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x35x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x35x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x35x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x3x35x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x35x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x364x364x1x14x14x1x1408x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x36x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x36x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x36x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x36x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x3711x3199x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3712x3200x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x3717x3205x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x378x378x1x14x14x1x1280x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x37x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x37x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x37x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x37x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x37x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x37x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x384x384x1x16x16x1x1024x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x16x16x1x1024x35x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x384x384x1x16x16x1x1024x8x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x16x16x1x1152x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x16x16x1x288x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x16x16x1x768x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x16x16x1x768x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x32x32x1x384x1x0x0x0x32x32x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x32x32x1x384x4x0x0x0x32x32x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x7x7x1x256x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x7x7x1x64x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x384x384x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x385x385x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x385x385x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x3x38x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x38x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x38x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x38x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x38x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x38x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x39x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x39x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x39x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x39x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x3x3x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x3x3x3x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x3x3x3x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x3x3x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x3x3x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x3x3x3x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x3x3x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x3x3x3x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x3x3x3x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x3x3x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x3x3x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x3x3x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x3x3x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 4, 8, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x3x3x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x3x408x408x1x7x7x1x48x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x4095x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4096x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4096x8192x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x40x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x40x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x40x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x40x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x40x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x4101x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4101x8197x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x416x416x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x416x416x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x416x416x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x420x420x1x14x14x1x1024x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x4223x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4224x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4229x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x42x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x42x21x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x22x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x23x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x24x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x42x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x42x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x42x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x42x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x42x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x42x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x42x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x42x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x42x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x42x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x431x431x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x431x431x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x431x431x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x431x431x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x431x431x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x431x431x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x431x431x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x432x432x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x432x432x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x432x432x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x433x433x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4351x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4351x3199x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4352x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4352x3200x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4357x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4357x3205x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4479x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4480x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4485x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x448x448x1x14x14x1x1152x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x14x14x1x2048x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x16x16x1x1280x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x16x16x1x768x16x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x16x16x1x768x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x16x16x1x832x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x16x16x1x832x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x448x448x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x44x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x44x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x44x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x44x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x44x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x4607x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4608x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4613x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x46x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x46x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x46x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x4735x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4735x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4736x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4736x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4741x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4741x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x48x52x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x54x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x66x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x68x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x74x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x4991x2687x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4991x2943x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4992x2688x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4992x2944x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4997x2693x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x4997x2949x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x4x4x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x4x4x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x4x4x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x3x4x4x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x3x4x4x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x4x4x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x4x4x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x4x4x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x4x4x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x4x4x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x4x4x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x4x4x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x4x4x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x3x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x50x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x50x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x50x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x58x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x50x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x62x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x70x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x50x72x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x76x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x50x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x78x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x50x82x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x5119x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x511x511x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x511x511x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5120x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5120x2816x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5125x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x5125x2821x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x512x512x1x14x14x1x1024x2x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x16x16x1x1024x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x16x16x1x1024x8x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x16x16x1x1152x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x32x32x1x768x4x0x0x0x32x32x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x16x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x512x512x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x512x512x1x4x4x1x96x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x4x4x1x96x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x512x512x1x7x7x1x128x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x3x512x864x1x16x16x1x330x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x512x864x1x16x16x1x384x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x513x513x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x513x513x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 8, 1, 1, 1>
2x3x513x513x1x3x3x1x48x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x513x513x1x3x3x1x48x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x513x513x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x513x513x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x513x513x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x518x518x1x14x14x1x768x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x5247x2559x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5248x2560x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5248x2816x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5253x2565x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5253x2821x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x52x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x52x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x52x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x54x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x54x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x54x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x54x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x54x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x56x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x56x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x56x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x56x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x56x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x576x1344x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x58x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x58x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x58x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x58x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x58x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x58x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x592x592x1x16x16x1x1024x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x592x592x1x16x16x1x768x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x5x5x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x5x5x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x601x601x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x60x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x60x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x60x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x60x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x62x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x639x1119x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x1183x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x1215x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x1247x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x1279x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x767x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x831x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x639x927x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1120x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1120x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1152x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x640x1184x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1184x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1216x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1216x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1248x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1248x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1280x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x1280x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x640x1x16x16x1x384x4x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x640x640x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x768x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x768x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x832x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x832x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x864x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x928x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x928x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x960x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x640x992x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x1125x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x1189x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x1221x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x1253x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x1285x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x773x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x837x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x645x933x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x64x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x64x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x64x64x1x15x15x1x80x30x7x7x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x15x15x1x80x6x7x7x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x15x15x1x80x8x7x7x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x3x3x1x160x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x3x3x1x160x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x3x3x1x160x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x64x64x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x64x64x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x64x64x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x7x7x1x16x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x64x64x1x7x7x1x80x30x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x7x7x1x80x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x64x64x1x7x7x1x80x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x66x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x66x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x66x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x66x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x66x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x66x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x66x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x66x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x66x66x1x4x4x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x66x66x1x4x4x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x66x66x1x4x4x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x671x1247x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x671x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x671x831x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x1024x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x1248x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x1248x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x1344x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x832x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x832x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x832x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x896x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x672x928x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x677x1253x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x677x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x677x837x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x68x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x68x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x68x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x68x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x68x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x6x6x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,4,32,32,1,1,1,2,2,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x6x6x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x6x6x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x6x6x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x703x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x703x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x1056x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x704x960x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x709x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x709x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x70x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x70x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x70x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x72x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x72x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x72x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x735x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x735x863x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x1120x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x1184x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x1312x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x1344x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x736x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x864x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x864x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x736x992x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x741x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x741x869x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x74x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x74x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x74x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x767x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x767x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1024x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1152x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1184x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1248x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1280x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x1344x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x704x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x768x928x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x76x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x76x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x76x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x773x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x773x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x78x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x799x1087x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x799x1215x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x799x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x799x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x799x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x799x863x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x7x7x1x3x3x1x4x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x3x7x7x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x7x7x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x3x7x7x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x7x7x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x3x800x1088x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x1088x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x1216x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x1216x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x1312x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x672x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x800x1x4x4x1x192x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x800x864x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x800x864x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x1093x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x1221x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x805x869x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x80x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x80x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x80x120x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x80x120x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x80x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x80x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x80x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x80x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x80x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x80x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x80x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x82x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x82x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x831x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x832x640x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x832x640x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x832x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x837x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x84x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x84x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x84x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x42x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x46x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x84x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x84x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x863x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x863x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x863x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x864x640x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x864x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x864x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x864x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x869x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x869x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x869x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x88x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x88x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x88x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x88x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x88x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x88x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x88x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x88x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x88x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x895x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x799x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x895x895x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x895x895x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x895x895x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x895x895x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x895x895x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x895x895x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x800x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x800x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x896x896x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x896x896x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x897x897x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x897x897x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x899x899x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x900x900x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x805x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x901x901x1x7x7x1x96x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x901x901x1x7x7x1x96x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x3x905x905x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x905x905x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x927x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x927x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x927x799x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x928x672x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x928x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x928x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x928x800x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x928x800x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x92x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x92x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x92x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x92x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x92x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x92x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x92x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x92x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x933x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x933x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x933x805x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,4,64,16,1,1,1,2,2,0,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x938x1448x1x1x1x1x4x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x3x938x1448x1x1x1x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,129[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x3x938x1448x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x3x938x1448x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x938x1448x1x3x3x1x32x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x938x1448x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,221[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x940x1450x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x940x1450x1x1x1x1x4x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x940x1450x1x1x1x1x4x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x3x940x1450x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x940x1450x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x940x1450x1x1x1x1x4x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x940x1450x1x1x1x1x4x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x3x940x1450x1x1x1x1x4x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x940x1450x1x1x1x1x4x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,1,7,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,129[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x940x1450x1x1x1x1x4x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,219[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x940x1450x1x1x1x1x4x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x3x940x1450x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x940x1450x1x3x3x1x32x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x959x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x959x671x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x959x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x960x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x960x672x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x960x704x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x960x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x960x960x1x16x16x1x768x1x0x0x0x16x16x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x3x965x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x965x677x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x965x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x96x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x96x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x96x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x96x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x96x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x3x96x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,4,1,64,1,1,1,1,1,4,1,64,4;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x3x96x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x3x96x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x3x991x639x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x991x703x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x992x640x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x992x640x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x992x704x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x992x736x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x992x768x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x997x645x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x997x709x1x7x7x1x64x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x400x128x128x1x3x3x1x400x1x1x1x0x1x1x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x400x128x128x1x3x3x1x400x1x1x1x0x2x2x0x1x1x0x0x25xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x400x128x128x1x3x3x1x400x4x1x1x0x2x2x0x1x1x0x0x25xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x400x256x256x1x3x3x1x400x4x1x1x0x1x1x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x400x28x28x1x3x3x1x400x4x1x1x0x1x1x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x400x512x512x1x3x3x1x400x4x1x1x0x2x2x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x400x64x64x1x3x3x1x400x1x1x1x0x1x1x0x1x1x0x0x25xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x4032x11x11x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4032x11x11x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x4032x7x7x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4040x1x1x1x1x1x1x1010x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4040x256x256x1x1x1x1x11110x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4040x256x256x1x1x1x1x11110x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4040x28x28x1x1x1x1x11110x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4040x512x512x1x3x3x1x4040x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x4040x56x56x1x3x3x1x4040x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x408x128x128x1x1x1x1x912x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x408x128x128x1x1x1x1x912x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x408x128x128x1x1x1x1x912x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x408x14x14x1x1x1x1x408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x408x14x14x1x1x1x1x912x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x408x14x14x1x3x3x1x408x4x1x1x0x1x1x0x1x1x0x0x17xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x408x28x28x1x3x3x1x408x1x1x1x0x2x2x0x1x1x0x0x17xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4096x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x128x128x1x3x3x1x4096x1x1x1x0x2x2x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x128x128x1x3x3x1x4096x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x12x12x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+1
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x4096x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x4096x14x14x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+1
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4096x14x14x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x4096x14x14x1x1x1x1x8192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x4096x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x4096x14x14x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4096x14x14x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x4096x14x14x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x14x14x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8
2x4096x15x15x1x3x3x1x4096x4x0x0x0x2x2x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x16x16x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4096x16x16x1x3x3x1x4096x4x1x1x0x1x1x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x1x1x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[4];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4096x1x1x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,6,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[6];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x1000x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,5,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x4096x1x1x1x1x1x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+16
2x4096x1x1x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+32
2x4096x1x1x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[5];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x4096x1x1x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4096x1x1x1x1x1x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[5];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 4, 1, 1>+32
2x4096x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x1x1x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x4096x1x1x1x1x1x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x1x1x1x1x1x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[5];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x4096x1x1x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x1x1x1x1x1x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x7x7x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,7,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[7];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,10;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x7x7x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[7];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[7];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x7x7x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[7];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x4096x1x1x1x7x7x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[7];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x4096x1x1x1x7x7x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x7x7x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[7];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x7x7x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[7];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x4096x1x1x1x7x7x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x1x1x1x7x7x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,7,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[7];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+128
2x4096x1x1x1x7x7x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x256x256x1x3x3x1x4096x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x256x256x1x3x3x1x4096x4x1x1x0x2x2x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x28x28x1x3x3x1x4096x4x1x1x0x2x2x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,272[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,91;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,91;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x30x46x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+8
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+8
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+8
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x4096x56x56x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x4096x56x56x1x3x3x1x4096x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x4096x56x56x1x5x5x1x2048x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4096x56x56x1x5x5x1x4096x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x4096x58x58x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4096x64x64x1x3x3x1x4096x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x4096x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,4,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x4096x7x7x1x3x3x1x4096x4x1x1x0x1x1x0x1x1x0x0x4096xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4096x7x7x1x7x7x1x512x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x4096x7x7x1x7x7x1x512x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
2x4096x7x7x1x7x7x1x512x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+128
2x4096x7x7x1x7x7x1x512x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x4096x7x7x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,7,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[7];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+64
2x4096x7x7x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x4096x7x7x1x7x7x1x512x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,7,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[7];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+128
2x4096x7x7x1x7x7x1x512x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4096x7x7x1x7x7x1x512x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,6,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[6];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x4096x7x7x1x7x7x1x512x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x4096x7x7x1x7x7x1x512x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,6,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[6];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+128
2x4096x7x7x1x7x7x1x512x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x4096x7x7x1x7x7x1x512x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,6,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[6];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+32
2x4096x7x7x1x7x7x1x512x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x4096x7x7x1x7x7x1x512x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+64
2x4096x7x7x1x7x7x1x512x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4096x8x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 128, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x4096x8x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x4096x8x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x4096x8x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+1
2x4096x8x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x4096x8x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x4096x8x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,300[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x4096x8x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x4096x8x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+1
2x4096x8x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x4096x8x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x1024x1024x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x112x112x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x112x112x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x40x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x112x112x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x40x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x112x112x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x16x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x32x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x40x112x112x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x40x112x112x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x112x112x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x40x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x128x128x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x128x128x1x1x1x1x90x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x40x128x128x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x132x132x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x40x14x14x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x40x14x14x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x40x14x14x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x150x150x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x192x128x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x192x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x192x128x1x1x1x1x32x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x192x128x1x1x1x1x32x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x192x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x192x128x1x1x1x1x32x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x192x128x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x40x192x128x1x1x1x1x32x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x192x128x1x1x1x1x32x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x40x192x128x1x3x3x1x40x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x192x128x1x3x3x1x40x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x40x192x128x1x3x3x1x40x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x192x128x1x3x3x1x40x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x192x128x1x3x3x1x40x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x40x192x128x1x3x3x1x40x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x192x128x1x3x3x1x40x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x40x192x128x1x3x3x1x40x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x40x1x1x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x1x1x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x40x1x1x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x1x1x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x40x1x1x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x1x1x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x40x1x1x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x1x1x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x40x1x1x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,2,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x40x1x1x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x1x1x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
2x40x256x256x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x40x256x256x1x1x1x1x215x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x40x256x256x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x256x256x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x40x256x256x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x256x256x1x7x7x1x40x1x3x3x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x257x257x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x40x28x28x1x1x1x1x60x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x28x28x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x40x28x28x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x28x28x1x1x1x1x90x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x512x512x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x512x512x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x40x512x512x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x512x512x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x160x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x40x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x5xNCHWxFP16xF=ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x512x512x1x3x3x1x40x4x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x512x512x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x512x512x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x512x512x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x40x512x512x1x7x7x1x40x1x3x3x0x1x1x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x56x56x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x56x56x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x56x56x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x2x2x1x80x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x3x3x1x40x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x56x56x1x3x3x1x40x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x40x56x56x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x57x57x1x3x3x1x160x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x64x64x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x64x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x64x64x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x64x64x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x1x1x1x32x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x96x64x1x1x1x1x32x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x32x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x40x96x64x1x1x1x1x32x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x1x1x1x32x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x32x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x40x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x40x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x40x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x40x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x40x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x40x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x40x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x40x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x40x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x40x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x40x96x64x1x1x1x1x48x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x48x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x48x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x40x96x64x1x1x1x1x96x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x1x1x1x96x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x40x96x64x1x3x3x1x40x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>+1
2x40x96x64x1x3x3x1x40x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x3x3x1x40x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x40x96x64x1x3x3x1x40x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x40x96x64x1x3x3x1x40x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x3x3x1x40x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x40x96x64x1x3x3x1x40x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x40x96x64x1x3x3x1x40x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x40x96x64x1x3x3x1x40x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x40x96x64x1x3x3x1x40x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x40x96x64x1x3x3x1x40x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x40x96x64x1x3x3x1x40x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x40x96x64x1x3x3x1x40x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x40x96x64x1x3x3x1x40x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x416x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x416x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x416x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x416x128x128x1x3x3x1x416x1x1x1x0x1x1x0x1x1x0x0x52xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x128x128x1x3x3x1x416x4x1x1x0x1x1x0x1x1x0x0x416xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x416x128x128x1x3x3x1x756x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,1,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,81[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x416x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x416x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x416x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x416x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x14x14x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x416x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x14x14x1x3x3x1x416x4x1x1x0x1x1x0x1x1x0x0x416xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x416x256x256x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x416x256x256x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x416x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x416x28x28x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x416x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x416x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x416x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x32x32x1x1x1x1x2496x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x416x7x7x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x416x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x7x7x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x416x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x416x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x416x7x7x1x1x1x1x1488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x416x7x7x1x1x1x1x1488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x416x7x7x1x1x1x1x2496x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x416x7x7x1x1x1x1x2496x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x419x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x419x64x64x1x1x1x1x2514x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x419x7x7x1x1x1x1x2514x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x41x256x256x1x1x1x1x246x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4224x32x32x1x3x3x1x4224x1x1x1x0x1x1x0x1x1x0x0x4224xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x4224x64x64x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x424x32x32x1x1x1x1x2544x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x424x64x64x1x1x1x1x2544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x424x7x7x1x1x1x1x2544x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x42x112x112x1x3x3x1x42x4x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvDepthwiseFwd2D:DeviceGroupedConvFwd<2, 64, BlockTileSize: 112, 112, FilterSize: 3,3, Dilation: 1, 1, Stride: 1, 1, Pad: 1, 1, NBatch: 2, SubTileH: 14, SubTileW: 16, InVectorWidth: 8, OutVectorWidth: 8, RequirePadding: 0>;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x42x128x128x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x42x165x165x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x42x165x165x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x42x165x165x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x42x166x166x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x42x169x169x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x42x256x256x1x1x1x1x245x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x42x28x28x1x1x1x1x245x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x42x28x28x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x42x28x28x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x42x83x83x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x42x83x83x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x42x83x83x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x42x83x83x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x42x83x83x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x42x83x83x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x42x83x83x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x42x83x83x1x3x3x1x42x64x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x42x83x83x1x3x3x1x42x64x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x42x83x83x1x3x3x1x42x64x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x42x83x83x1x5x5x1x42x64x2x2x0x1x1x0x1x1x0x0x42xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x42x83x83x1x5x5x1x42x64x2x2x0x1x1x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x42x83x83x1x5x5x1x42x64x2x2x0x1x1x0x1x1x0x0x42xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x42x83x83x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xB=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x42x83x83x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x42x83x83x1x7x7x1x42x64x3x3x0x1x1x0x1x1x0x0x42xNCHWxFP32xB=ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x42x83x83x1x7x7x1x42x64x3x3x0x1x1x0x1x1x0x0x42xNCHWxFP32xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x42x83x83x1x7x7x1x42x64x3x3x0x1x1x0x1x1x0x0x42xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x42x85x85x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xB=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x42x85x85x1x5x5x1x42x64x2x2x0x2x2x0x1x1x0x0x42xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4320x64x64x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x432x1025x1025x1x3x3x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x128x128x1x1x1x1x84x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x128x128x1x3x3x1x432x4x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x128x128x1x3x3x1x432x4x1x1x0x1x1x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x128x128x1x5x5x1x432x1x2x2x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x128x128x1x5x5x1x432x4x2x2x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x129x129x1x3x3x1x432x1x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x129x129x1x3x3x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x12x12x1x3x3x1x432x1x0x0x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x432x131x131x1x5x5x1x432x1x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x432x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x432x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x432x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x72x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x432x14x14x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x1x1x1x72x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x432x14x14x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x1x1x1x72x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x432x14x14x1x1x1x1x84x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+16
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x432x14x14x1x3x3x1x432x16x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x432x14x14x1x3x3x1x432x4x1x1x0x1x1x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x432x14x14x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x14x14x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x432x15x15x1x3x3x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x16x16x1x3x3x1x432x4x0x0x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x1x1x1x1x1x1x18x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x256x256x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x256x256x1x5x5x1x432x4x2x2x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x259x259x1x5x5x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x261x261x1x7x7x1x432x1x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x261x261x1x7x7x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x432x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x432x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x432x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x432x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x432x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x432x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x432x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x432x29x29x1x3x3x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x512x512x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x432x64x64x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x64x64x1x1x1x1x84x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x64x64x1x7x7x1x432x1x3x3x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x66x66x1x3x3x1x432x1x0x0x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x66x66x1x5x5x1x432x4x2x2x0x1x1x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x67x67x1x3x3x1x432x4x0x0x0x2x2x0x1x1x0x0x432xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x432x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x432x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x432x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x432x7x7x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x432x7x7x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x16x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x432x7x7x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x432x7x7x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x32x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x432x7x7x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x432x7x7x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x432x7x7x1x5x5x1x432x64x2x2x0x2x2x0x1x1x0x0x432xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x436x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x436x128x128x1x3x3x1x436x4x1x1x0x1x1x0x1x1x0x0x436xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x436x64x64x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x436x64x64x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x440x128x128x1x3x3x1x440x4x1x1x0x2x2x0x1x1x0x0x55xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x440x64x64x1x3x3x1x440x1x1x1x0x2x2x0x1x1x0x0x55xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x440x64x64x1x3x3x1x440x4x1x1x0x1x1x0x1x1x0x0x55xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x443x128x128x1x5x5x1x443x4x2x2x0x1x1x0x1x1x0x0x443xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x443x14x14x1x5x5x1x443x1x2x2x0x1x1x0x1x1x0x0x443xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x443x1x1x1x1x1x1x30x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x448x118x181x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x448x118x181x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x118x181x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x448x118x181x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x181x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x181x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x181x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x181x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x10x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x12x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x16x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x181x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x181x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x181x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x118x182x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x118x182x1x1x1x1x224x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x448x118x182x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x448x118x182x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x448x118x182x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x448x118x182x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x448x118x182x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x224x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,68[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x118x182x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x182x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x182x1x1x1x1x896x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x118x182x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x1x1x1x896x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x3x3x1x448x2x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x6x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x7x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x118x182x1x3x3x1x448x8x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x118x182x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x118x182x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x448x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x128x128x1x1x1x1x1232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x448x128x128x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x128x128x1x3x3x1x160x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x128x128x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x12x12x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x131x131x1x5x5x1x448x1x0x0x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x448x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x448x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,254[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x448x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x448x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x14x14x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x448x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x16x16x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x16x16x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x16x16x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x16x16x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x16x16x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x448x16x16x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x16x16x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x16x16x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x448x16x16x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x16x16x1x1x1x1x2688x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[6];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[7];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x1x1x1x1x1x1x56x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x448x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x448x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x448x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x362x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x362x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x362x1x3x3x1x448x10x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x362x1x3x3x1x448x12x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x362x1x3x3x1x448x14x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x362x1x3x3x1x448x16x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x362x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x448x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x448x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x235x363x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x235x363x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x2x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x363x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x363x1x3x3x1x448x6x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x363x1x3x3x1x448x7x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x235x363x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x235x363x1x3x3x1x448x8x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x256x256x1x1x1x1x1232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x256x256x1x1x1x1x1232x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x256x256x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x256x256x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x256x256x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x256x256x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x256x256x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x256x256x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x256x256x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x256x256x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x256x256x1x3x3x1x448x4x1x1x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x259x259x1x5x5x1x448x4x0x0x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x28x28x1x1x1x1x1232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x1232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x448x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x448x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x448x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x28x28x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x28x28x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x31x31x1x5x5x1x448x1x0x0x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x31x31x1x5x5x1x448x4x0x0x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x448x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x4x1024x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x448x4x16384x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x448x4x4x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x4x4x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x448x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x448x4x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x56x56x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x56x56x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x56x56x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x62x62x1x1x1x1x2080x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x448x62x62x1x1x3x1x512x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x62x62x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x64x64x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x448x64x64x1x3x3x1x448x1x1x1x0x2x2x0x1x1x0x0x448xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x448x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x448x6x6x1x3x3x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x448x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x6x6x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x448x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x448x6x8x1x3x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x448x7x7x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x6x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x448x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x448x8x8x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x448x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x448x8x8x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x448x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x448x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x448x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x448x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x448x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x448x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x448x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x448x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x448x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x448x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x448x8x8x1x1x3x1x384x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x448x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x448x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x448x8x8x1x1x3x1x384x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x448x8x8x1x1x3x1x384x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x448x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x448x8x8x1x1x3x1x384x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x448x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x448x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x448x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x448x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x448x8x8x1x1x3x1x384x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x448x8x8x1x1x3x1x384x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x448x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x1x3x1x512x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x448x8x8x1x3x1x1x384x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x448x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x448x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x448x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x1x1x512x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x1x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x1x1x512x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x448x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x1x1x512x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x1x1x512x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x448x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x448x8x8x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+1
2x448x8x8x1x3x3x1x384x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x448x8x8x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x448x8x8x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x448x8x8x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x384x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x448x8x8x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x448x8x8x1x3x3x1x512x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x448x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x44x128x128x1x3x3x1x176x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x128x128x1x3x3x1x44x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x14x14x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x1x1x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x256x256x1x1x1x1x68x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x28x28x1x1x1x1x68x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x28x28x1x3x3x1x176x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x28x28x1x3x3x1x44x1x1x1x0x2x2x0x1x1x0x0x44xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x44x28x28x1x3x3x1x44x4x1x1x0x2x2x0x1x1x0x0x44xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x44x512x512x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x44x64x64x1x3x3x1x352x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x450x128x128x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x450x256x256x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x453x32x32x1x1x1x1x2718x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4608x64x64x1x5x5x1x4608x1x2x2x0x1x1x0x1x1x0x0x4608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x462x1x1x1x1x1x1x38x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x462x28x28x1x1x1x1x100x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x464x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x464x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x464x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x464x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x464x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x464x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x464x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x464x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x464x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x464x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x474x14x14x1x1x1x1x94x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x474x1x1x1x1x1x1x39x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x474x256x256x1x3x3x1x474x1x1x1x0x2x2x0x1x1x0x0x474xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x474x28x28x1x3x3x1x474x4x1x1x0x2x2x0x1x1x0x0x474xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x474x64x64x1x1x1x1x94x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x47x512x512x1x3x3x1x18x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x47x512x512x1x3x3x1x18x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x480x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x128x128x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x128x128x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x128x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x128x128x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x128x128x1x3x3x1x480x4x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x128x128x1x3x3x1x960x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x128x128x1x3x3x1x960x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x12x12x1x3x3x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,61;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x12x12x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x12x12x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x12x12x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x480x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x480x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x480x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x14x14x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x480x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x2880x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x480x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x480x14x14x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,61;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x16x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x32x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x3x3x1x480x64x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x480x14x14x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x3x3x1x960x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x14x14x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x5x5x1x480x16x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x480x14x14x1x5x5x1x480x1x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x14x14x1x5x5x1x480x32x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x480x14x14x1x5x5x1x480x4x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x14x14x1x5x5x1x480x64x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x480x150x150x1x5x5x1x480x4x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x15x15x1x3x3x1x480x1x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x15x15x1x5x5x1x480x1x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x18x18x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x1x1x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x256x256x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x256x256x1x3x3x1x480x1x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x256x256x1x5x5x1x480x1x2x2x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x256x256x1x5x5x1x480x4x2x2x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x28x28x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x480x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x28x28x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x480x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x480x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x28x28x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x28x28x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x28x28x1x5x5x1x480x1x2x2x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x28x28x1x5x5x1x480x4x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x30x30x1x3x3x1x480x1x0x0x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x32x32x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x32x32x1x5x1x1x480x1x2x0x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x37x37x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x37x37x1x3x3x1x480x1x0x0x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x48x32x1x1x1x1x128x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x48x32x1x1x1x1x128x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x48x32x1x1x1x1x128x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x48x32x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x48x32x1x1x1x1x128x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x48x32x1x1x1x1x128x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x128x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x48x32x1x1x1x1x128x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x48x32x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x128x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x48x32x1x1x1x1x480x10x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x10x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x10x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x48x32x1x1x1x1x480x11x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x11x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x11x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x48x32x1x1x1x1x480x12x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x12x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x12x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x480x48x32x1x1x1x1x480x13x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x13x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x13x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x480x48x32x1x1x1x1x480x14x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x14x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x14x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x48x32x1x1x1x1x480x15x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x15x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x15x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x17x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x17x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x17x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x18x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x18x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x18x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x19x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x19x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x19x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x48x32x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x48x32x1x1x1x1x480x20x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x20x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x20x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x21x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x21x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x21x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x22x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x22x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x22x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x23x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x23x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x23x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x24x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x25x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x25x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x25x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x26x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x26x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x26x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x27x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x27x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x27x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x28x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x28x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x28x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x29x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x29x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x29x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x48x32x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x48x32x1x1x1x1x480x30x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x30x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x30x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x31x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x31x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x31x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x33x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x33x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x33x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x34x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x34x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x34x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x35x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x35x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x35x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x36x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x36x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x36x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x480x48x32x1x1x1x1x480x37x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x37x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x37x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x480x48x32x1x1x1x1x480x3x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x3x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x3x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x48x32x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x48x32x1x1x1x1x480x5x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x5x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x5x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x48x32x1x1x1x1x480x6x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x6x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x6x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x48x32x1x1x1x1x480x7x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x7x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x7x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x48x32x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x48x32x1x1x1x1x480x9x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x48x32x1x1x1x1x480x9x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x48x32x1x1x1x1x480x9x0x0x0x1x1x0x1x1x0x0x5xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x480x4x1024x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x512x512x1x3x3x1x480x4x1x1x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x56x56x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x56x56x1x3x3x1x480x1x1x1x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x56x56x1x3x3x1x480x4x1x1x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x64x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x64x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x64x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x480x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x480x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x480x64x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x480x64x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x64x128x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x480x64x64x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x64x64x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x64x64x1x1x1x1x2880x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x64x64x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x480x64x64x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x64x64x1x5x1x1x480x1x2x0x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x64x64x1x7x7x1x480x1x3x3x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x64x64x1x9x9x1x480x1x4x4x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x480x75x75x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x480x77x77x1x3x3x1x480x4x0x0x0x2x2x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x480x7x7x1x1x1x1x120x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x480x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x480x7x7x1x1x1x1x120x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x480x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x480x7x7x1x1x1x1x120x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x480x7x7x1x1x1x1x120x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x480x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x480x7x7x1x1x5x1x480x4x0x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x7x7x1x3x3x1x480x1x1x1x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x480x7x7x1x5x1x1x480x1x2x0x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x480x7x7x1x5x5x1x480x1x2x2x0x1x1x0x1x1x0x0x480xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x486x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x486x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x486x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x486x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x486x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x486x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x486x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x486x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x486x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x487x7x7x1x1x1x1x2922x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x487x7x7x1x1x1x1x2922x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x488x14x14x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x488x14x14x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x488x14x14x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x14x14x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x14x14x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x14x14x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x14x14x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x488x7x7x1x1x1x1x488x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x488x7x7x1x1x1x1x488x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x16x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x488x7x7x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x488x7x7x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x16x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x488x7x7x1x3x3x1x488x64x1x1x0x1x1x0x1x1x0x0x488xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x488x7x7x1x3x3x1x488x64x1x1x0x2x2x0x1x1x0x0x488xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x48x1024x1024x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1024x1024x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1024x1024x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1024x1024x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1024x1024x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x1024x1024x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1024x1024x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x1025x1025x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x1025x1025x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x1025x1025x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x1025x1025x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x1026x1026x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x1026x1026x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x1026x1026x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x1026x1026x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x102x102x1x3x3x1x96x1x0x0x0x3x3x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x10x10x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x112x112x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x112x112x1x1x1x1x48x4x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x112x112x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x112x112x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x112x112x1x7x7x1x48x1x3x3x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x113x113x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x125x125x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x128x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x128x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x128x128x1x1x1x1x68x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x48x128x128x1x2x2x1x88x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x128x128x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x128x128x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x128x128x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x128x128x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x128x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x13x13x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,8,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[10];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x13x13x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x13x13x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x48x14x14x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x14x14x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x48x14x14x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x48x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x48x14x14x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+64
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x14x14x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x14x14x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x14x14x1x5x5x1x16x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x5x5x1x16x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x48x14x14x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x48x14x14x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x5x5x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x5x5x1x16x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+32
2x48x14x14x1x5x5x1x16x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x48x14x14x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x5x5x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x48x14x14x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+16
2x48x14x14x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x5x5x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x5x5x1x16x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x14x14x1x5x5x1x16x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x14x14x1x5x5x1x16x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x14x14x1x5x5x1x16x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x14x14x1x5x5x1x512x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x5x5x1x512x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x5x5x1x512x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x48x14x14x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x48x14x14x1x5x5x1x512x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x14x14x1x5x5x1x512x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,3,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x48x14x14x1x5x5x1x512x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x5x5x1x512x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x48x14x14x1x5x5x1x512x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x5x5x1x512x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x14x14x1x5x5x1x512x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x5x5x1x512x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x14x14x1x5x5x1x512x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x14x14x1x7x7x1x48x1x3x3x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x14x14x1x7x7x1x48x4x3x3x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x16x16x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x16x16x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x16x16x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x48x16x16x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x16x16x1x3x3x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x48x16x16x1x3x3x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x16x16x1x4x4x1x48x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x18x18x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x18x18x1x3x3x1x16x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x18x18x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x48x18x18x1x3x3x1x16x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x18x18x1x3x3x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x18x18x1x3x3x1x16x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x1x1x1x1x1x1x1104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x1x1x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x48x1x1x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+1
2x48x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x48x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+1
2x48x1x1x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x1x1x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x1x1x1x1x1x1x196x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x1x1x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x736x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x1x1x1x1x1x1x798x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x806x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x228x228x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x228x228x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x24x16x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x24x16x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x24x16x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x24x16x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x24x16x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x24x16x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x24x16x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x24x16x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x24x16x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x24x16x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x24x16x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x24x16x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x24x16x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x24x16x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x24x16x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x24x16x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x24x16x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x24x16x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x24x16x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x255x255x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x48x255x255x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x255x255x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x48x255x255x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x256x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x256x256x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x256x256x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x256x256x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x48x256x256x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x256x256x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x48x256x256x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x256x256x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x256x256x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x256x256x1x5x5x1x96x1x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x257x257x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x257x257x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x257x257x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x257x257x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x48x257x257x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x27x27x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x192x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x48x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x48x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x48x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x27x27x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x27x27x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x27x27x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x27x27x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x27x27x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x27x27x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x28x28x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x28x28x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x48x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x28x28x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x28x28x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x28x28x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x28x28x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x28x28x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x48x28x28x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x48x28x28x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x48x28x28x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x28x28x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x28x28x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x48x28x28x1x7x7x1x48x1x3x3x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x31x31x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x31x31x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x48x32x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x32x32x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x32x32x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x32x32x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x32x32x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x33x33x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x48x33x33x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x33x33x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x48x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x48x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x48x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x48x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x48x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x35x35x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x48x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x5x5x1x64x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x35x35x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x35x35x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x35x35x1x5x5x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x35x35x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x35x35x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x35x35x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x35x35x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x35x35x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x35x35x1x5x5x1x64x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x37x37x1x3x3x1x64x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x37x37x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x3x3x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x48x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x48x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x48x32x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x48x48x32x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x48x48x32x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x48x32x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x48x32x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x48x32x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x48x32x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x48x32x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x48x32x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x48x32x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x48x32x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x48x32x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x48x32x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x48x48x32x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x48x32x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x32x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x48x32x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x48x32x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x48x48x48x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x4x4x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x1x1x1x112x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x1x1x1x416x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x1x1x1x48x4x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x512x512x1x2x2x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x512x512x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x512x512x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x512x512x1x3x3x1x76x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x512x512x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x512x512x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x512x512x1x7x7x1x48x1x3x3x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x512x512x1x9x9x1x48x1x4x4x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x513x513x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x48x513x513x1x3x3x1x48x4x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x515x515x1x5x5x1x48x4x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x48x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[8];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:12
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x48x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x48x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+128
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x56x56x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 4>+128
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x48x56x56x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x56x56x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x48x56x56x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x56x56x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x48x56x56x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x48x56x56x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x32x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x48x56x56x1x3x3x1x48x64x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x56x56x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x56x56x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x48x16x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x48x32x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x48x64x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x56x56x1x5x5x1x96x4x2x2x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x7x7x1x96x1x3x3x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x56x56x1x9x9x1x48x4x4x4x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x57x57x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x59x59x1x5x5x1x48x1x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x5x5x1x3x3x1x48x1x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x5x5x1x3x3x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x64x128x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x64x128x1x5x5x1x16x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x48x64x64x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x64x64x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x48x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x64x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x64x64x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x6x6x1x3x3x1x48x4x0x0x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x74x74x1x4x4x1x48x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x7x7x1x1x1x1x832x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x48x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x48x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x7x7x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[6];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x48x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x48x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x7x7x1x1x1x1x832x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x48x7x7x1x1x1x1x832x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x48x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x48x7x7x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x48x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x48x7x7x1x1x1x1x832x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x1x1x1x832x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x48x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x7x7x1x3x3x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x48x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x7x7x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x48x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,115;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,199;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x48x7x7x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+1
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,217;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x48x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x7x7x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x7x7x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[8];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x48x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x48x7x7x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x48x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,130;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x48x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x48x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x48x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x48x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x48x7x7x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x48x7x7x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x48x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x48x7x7x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x48x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x8x8x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x48x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x48x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x48x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x48x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x48x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x48x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x48x96x64x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x10x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x10x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x3x3x1x48x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x11x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x11x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x3x3x1x48x12x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x12x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x13x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x13x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x14x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x14x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x15x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x15x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x17x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x17x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x18x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x18x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x96x64x1x3x3x1x48x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x19x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x19x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x3x3x1x48x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x20x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x20x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x48x96x64x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x21x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x21x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x22x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x22x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x23x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x23x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x24x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x24x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x25x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x25x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x26x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x26x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x27x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x27x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x28x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x28x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x29x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x29x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x30x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x30x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x31x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x31x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x48x96x64x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x33x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x34x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x35x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x36x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x96x64x1x3x3x1x48x36x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x37x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x37x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x3x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x48x96x64x1x3x3x1x48x3x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x5x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x5x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x3x3x1x48x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x6x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x3x3x1x48x6x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x7x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x7x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x9x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x3x3x1x48x9x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x10x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x11x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x12x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x13x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x14x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x15x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x16x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 4, 1, 1>+1
2x48x96x64x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x17x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x18x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x19x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x48x96x64x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x48x96x64x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x20x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x21x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x48x96x64x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x22x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x23x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x24x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x25x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x26x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x27x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x28x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x29x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x48x96x64x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x2x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x48x96x64x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x30x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x31x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x32x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x33x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x34x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x48x96x64x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x35x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x36x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x37x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x48x96x64x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x96x64x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x3x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x48x96x64x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x4x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x5x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x48x96x64x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x6x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x48x96x64x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x7x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,305;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x48x96x64x1x5x5x1x48x8x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x64x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,317;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x48x96x64x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x48x96x64x1x5x5x1x48x9x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x48x96x96x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x48x96x96x1x7x7x1x48x1x3x3x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x97x97x1x3x3x1x48x1x0x0x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x48x9x9x1x3x3x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x48x9x9x1x3x3x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x490x64x64x1x1x1x1x2022x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x4920x128x128x1x3x3x1x4920x4x1x1x0x2x2x0x1x1x0x0x15xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4920x1x1x1x1x1x1x492x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x4920x32x32x1x1x1x1x4920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x492x128x128x1x3x3x1x237x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x492x14x14x1x3x3x1x237x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x492x1x1x1x1x1x1x4920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x492x512x512x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x492x512x512x1x3x3x1x492x4x1x1x0x1x1x0x1x1x0x0x492xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4944x64x64x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x4944x64x64x1x1x1x1x824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x4944x64x64x1x5x5x1x4944x4x2x2x0x1x1x0x1x1x0x0x4944xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x499x128x128x1x3x3x1x289x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x499x14x14x1x3x3x1x289x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x499x64x64x1x3x3x1x289x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x49x192x128x1x3x3x1x32x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x192x128x1x3x3x1x32x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x49x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x49x256x256x1x1x1x1x142x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x49x256x256x1x3x3x1x49x1x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x49x28x28x1x1x1x1x142x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x49x512x512x1x3x3x1x49x4x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x4x100x1x1x4x1x1x192x10x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x11x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x12x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x13x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x14x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x15x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x16x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x17x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x18x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x19x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x1x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x20x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x21x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x22x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x23x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x24x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x25x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x26x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x27x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x28x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x29x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x2x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x30x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x31x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x32x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x33x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x34x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x35x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x36x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x37x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x3x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x4x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x5x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x6x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x7x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x100x1x1x4x1x1x192x8x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x100x1x1x4x1x1x192x9x0x0x0x4x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x1024x1024x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x11x11x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x11x11x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x128x128x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x128x128x1x2x2x1x1152x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x128x128x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x12x12x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x12x12x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x12x12x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x12x12x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x4x12x12x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x4x12x12x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x12x12x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x12x12x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x12x12x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x4x12x12x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x12x12x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x4x12x12x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x12x12x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x12x12x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x4x13x13x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x13x13x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x4x13x13x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x4x13x13x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x4x13x13x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x13x13x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x4x13x13x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x13x13x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x13x13x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x16x16x1x1x1x1x4x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x16x16x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x16x16x1x3x3x1x512x140x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,1,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x4x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x4x1x1x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x4x1x1x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x4x1x1x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x4x1x1x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x1x1x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x1x1x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+4
2x4x224x224x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x4x225x225x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x4x299x299x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x2x2x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x2x2x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x4x2x2x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x2x2x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,31[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x4x2x2x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x2x2x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x32x32x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x32x32x1x3x3x1x320x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x32x32x1x3x3x1x512x140x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x4x32x32x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x32x32x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x3x3x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x4x3x3x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x4x3x3x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x3x3x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x3x3x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x450x450x1x2x2x1x16x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x450x450x1x2x2x1x16x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+32
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[3];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x4x4x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x4x4x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x4x4x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x512x512x1x3x3x1x4x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x5x5x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x64x64x1x1x1x1x4x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x4x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
2x4x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x64x64x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x6x6x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x6x6x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,0,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,68;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x4x6x6x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[6];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x4x6x6x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x4x6x6x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x4x6x6x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x4x6x6x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x4x7x7x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x7x7x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x7x7x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x7x7x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x7x7x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x7x7x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x80x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x4x8x8x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x8x8x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x8x8x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x8x8x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x8x8x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x8x8x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x938x1448x1x1x1x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x940x1450x1x1x1x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x4x96x96x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x4x9x9x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x9x9x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x9x9x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x9x9x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x9x9x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x4x9x9x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x502x128x128x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x502x128x128x1x5x5x1x502x1x2x2x0x1x1x0x1x1x0x0x502xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x502x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x502x32x32x1x1x1x1x2042x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x502x64x64x1x1x1x1x2042x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x504x128x128x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x504x128x128x1x5x5x1x504x4x2x2x0x2x2x0x1x1x0x0x504xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x504x14x14x1x1x1x1x95x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x504x14x14x1x3x3x1x504x1x1x1x0x1x1x0x1x1x0x0x504xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x504x32x32x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x505x1x1x1x1x1x1x2020x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x505x1x1x1x1x1x1x4040x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x508x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x508x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x508x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x50x1x1x1x1x1x1x600x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x50x28x28x1x1x1x1x300x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x50x56x56x1x1x1x1x300x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:225
2x510x10x10x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:233
2x510x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:248
2x510x10x10x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+4
2x510x10x10x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+4
2x510x10x10x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+4
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:227
2x510x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,5,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];TransposedConvBinWinoRxS<3-2>:37
2x510x10x10x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+2
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[3];TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];TransposedConvBinWinoRxS<3-2>:48
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:227
2x510x10x10x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x10x10x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:256
2x510x10x10x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:251
2x510x19x19x1x3x3x1x512x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,172
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:247
2x510x19x19x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];TransposedConvBinWinoRxS<3-2>:242
2x510x19x19x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:203
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:251
2x510x19x19x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,5,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[5];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:113
2x510x19x19x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:202
2x510x19x19x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:120
2x510x19x19x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,170[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[1];TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,16,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,4,1,4,1,64,78[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+2
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:233
2x510x19x19x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x19x19x1x3x3x1x512x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x19x19x1x3x3x1x512x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[2];TransposedConvBinWinoRxS<3-2>:232
2x510x19x19x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x510x5x5x1x3x3x1x256x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:115
2x510x5x5x1x3x3x1x256x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:140
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:130
2x510x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:141
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:146
2x510x5x5x1x3x3x1x256x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:130
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:137
2x510x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:135
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x510x5x5x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x510x5x5x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+4
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+4
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[5];TransposedConvBinWinoRxS<3-2>:25
2x510x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:161
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,107[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+2
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:256
2x510x5x5x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:135
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[6];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 8, 1, 1>+32
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+-1
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+32
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+32
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[6];TransposedConvBinWinoRxS<3-2>:13
2x510x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:139
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];TransposedConvBinWinoRxS<3-2>:33
2x510x5x5x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:128
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 8, 1, 1>+32
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+32
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+16
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[6];TransposedConvBinWinoRxS<3-2>:9
2x510x5x5x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:146
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,244[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];TransposedConvBinWinoRxS<3-2>:256
2x510x5x5x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:134
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+2
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,284
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];TransposedConvBinWinoRxS<3-2>:72
2x510x5x5x1x3x3x1x256x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:147
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+16
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+1
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,4,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,274[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+8
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,276
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[4];TransposedConvBinWinoRxS<3-2>:78
2x510x5x5x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:128
2x511x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x511x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x5120x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x5120x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1008x1008x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1008x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1008x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1008x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1008x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1008x1008x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1008x1040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x1008x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1008x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1008x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1008x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1008x1040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x1008x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1008x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1008x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1008x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1008x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1008x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1008x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x100x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x100x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x100x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x100x108x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x100x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x100x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x100x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x100x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x100x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x100x132x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x100x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x136x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x136x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x100x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x100x136x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x100x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x136x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x136x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x140x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x100x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x100x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x100x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x100x152x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x152x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x100x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x152x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x152x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x152x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x152x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x100x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x100x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x100x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x100x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x100x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x100x164x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x164x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x100x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x100x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x164x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x100x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x100x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x100x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x100x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x100x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x100x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x100x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x100x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x100x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x100x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x100x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x100x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x100x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x100x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x100x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x100x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x100x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x100x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x100x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x100x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x100x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x100x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x100x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1]
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x1024x1024x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x1024x1024x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x1024x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x1024x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1024x1024x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x1024x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4095x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4095x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x103x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x103x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x103x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x103x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x103x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x103x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x103x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x103x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x103x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x103x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x1040x1008x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x1040x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1040x1008x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1040x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1040x1008x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1040x1008x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1040x1040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1040x1040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1040x1040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x1040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4079x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4080x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4081x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4111x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1040x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1040x4113x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x104x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x104x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x104x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x104x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x104x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x104x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x104x80x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x104x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x104x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x104x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x104x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x104x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x104x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x104x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x104x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x104x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x104x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x104x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x104x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x104x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x104x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x104x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x104x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x104x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x104x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x104x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x104x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x104x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x105x105x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x105x105x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x105x105x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x105x105x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x105x105x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x105x105x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x105x105x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x105x105x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x106x106x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x106x106x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x512x106x106x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x106x106x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x512x106x106x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x106x106x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x106x106x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x106x106x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x107x107x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x107x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x107x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x107x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x107x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x107x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x107x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x107x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x107x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x107x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x107x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x108x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x108x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x108x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x108x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x108x108x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x108x108x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x108x108x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x108x108x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x108x80x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x108x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x108x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x108x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x108x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x108x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x108x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x108x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x108x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x108x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x108x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x108x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x108x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x108x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x108x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x108x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x108x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x108x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x108x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x108x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x108x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x108x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x109x109x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x109x109x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x109x109x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x109x109x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:230
2x512x10x10x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:243
2x512x10x10x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:4
2x512x10x10x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:83
2x512x10x10x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:11
2x512x10x10x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:120
2x512x10x10x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x1x1x1x128x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:157
2x512x10x10x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x10x1x1x1x1x2048x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x1x1x1x2048x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x512x10x10x1x1x1x1x2048x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x10x10x1x1x1x1x2048x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x1x1x1x2048x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x1x1x1x2048x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x1x1x1x2048x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x10x10x1x1x1x1x2048x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x1x1x1x2048x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x1x1x1x2048x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x10x10x1x1x1x1x2048x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x10x10x1x1x1x1x2048x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x1x1x1x2048x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x1x1x1x2048x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x10x10x1x1x1x1x2048x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x10x10x1x1x1x1x2048x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x1x1x1x2048x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x10x10x1x1x1x1x2048x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x10x10x1x1x1x1x2048x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x1x1x1x2048x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x1x1x1x2048x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x10x10x1x1x1x1x2048x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x10x10x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x10x10x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:238
2x512x10x10x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:248
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:228
2x512x10x10x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:240
2x512x10x10x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:202
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:193
2x512x10x10x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:230
2x512x10x10x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:36
2x512x10x10x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:42
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:33
2x512x10x10x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:57
2x512x10x10x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:243
2x512x10x10x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:250
2x512x10x10x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x10x10x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x10x10x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x10x10x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x486x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:229
2x512x10x10x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:229
2x512x10x10x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:244
2x512x10x10x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:221
2x512x10x10x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:55
2x512x10x10x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:36
2x512x10x10x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:239
2x512x10x10x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x10x10x1x3x3x1x510x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:231
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:228
2x512x10x10x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:199
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:196
2x512x10x10x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];TransposedConvBinWinoRxS<3-2>:69
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];TransposedConvBinWinoRxS<3-2>:81
2x512x10x10x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x10x42x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x10x42x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x10x42x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x10x42x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x10x42x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x10x42x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x10x42x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x10x42x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x10x42x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x10x42x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x10x42x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x10x42x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x10x42x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x10x42x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x10x42x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x10x42x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x10x42x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x10x42x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x10x42x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x10x42x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x10x42x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x42x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x10x42x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x42x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x10x42x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x10x42x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x10x42x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x10x42x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x10x42x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x10x42x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x111x111x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x111x111x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x111x111x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x111x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x111x111x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x111x111x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x111x111x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x111x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x111x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x111x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x111x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x111x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x111x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x111x99x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x111x99x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x111x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x1128x896x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1128x928x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x112x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x112x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x112x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x112x100x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x112x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x112x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x112x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x512x112x112x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x512x112x112x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x112x112x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x512x112x112x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x512x112x112x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x512x112x112x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 128, Filter1x1Pad0, 32, 32, 2, 2, 16, 16, 16, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x112x112x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7]
2x512x112x112x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x512x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x512x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,2[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x112x112x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5]
2x512x112x112x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x512x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[3]
2x512x112x112x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[4]
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x112x112x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x112x112x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x112x112x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x112x112x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 128, Default, 32, 32, 2, 2, 16, 16, 16, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x112x112x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x112x112x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x112x112x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x112x112x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x112x112x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x112x112x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x112x112x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x112x112x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[3];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x112x112x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194
2x512x112x112x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x112x112x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:133
2x512x112x112x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 128, OddC, 32, 32, 2, 2, 16, 16, 16, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x112x112x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x112x112x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x112x112x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x112x112x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x112x112x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x112x112x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,185[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+32
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x112x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x112x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x112x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x112x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x112x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x112x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x112x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x112x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x112x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x112x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x112x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x112x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x112x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x112x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x112x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x112x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x112x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x112x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x112x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x112x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x112x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x112x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x112x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x112x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x112x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x112x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x113x113x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x113x113x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x113x113x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x113x113x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x113x113x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x113x113x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x113x113x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x113x113x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x113x113x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x113x113x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x113x113x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x113x113x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+16
2x512x113x113x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,9,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+16
2x512x113x113x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1144x912x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1144x912x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1144x912x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x114x114x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x114x114x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x114x114x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x114x114x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x114x114x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x114x114x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x114x114x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x114x114x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x512x114x114x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x114x114x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x114x114x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x114x114x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x115x115x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x115x115x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x115x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x115x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x115x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x115x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x115x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x115x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x115x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x115x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x115x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x1160x896x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x1160x928x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x116x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x116x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x116x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x116x116x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x116x116x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x116x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x116x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x116x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x116x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x116x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x116x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x116x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x116x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x116x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x116x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x116x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x116x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x116x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x116x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x116x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x116x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x116x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x116x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x116x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x116x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x116x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x117x117x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x117x117x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x117x117x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x117x117x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x117x117x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x117x117x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x119x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x119x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x119x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x119x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x119x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x119x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x119x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x119x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x119x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x119x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x119x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x119x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x11x11x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x11x11x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x11x11x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x11x11x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x11x11x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x11x11x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x11x11x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x120x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x120x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x120x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x120x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x120x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x120x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x120x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x120x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x120x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x120x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x120x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x120x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x120x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x120x88x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x120x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x120x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x120x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x120x88x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x120x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x120x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x120x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x120x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x120x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x120x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x120x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x120x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x120x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x120x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x120x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x120x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x120x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x120x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x120x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x123x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x123x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x123x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x123x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x123x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x123x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x123x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x123x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x123x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x124x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x124x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x124x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x124x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x124x80x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x124x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x124x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x124x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x124x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x124x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x124x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x124x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x124x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x124x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x124x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x124x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x124x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x124x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x124x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x124x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x124x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x124x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x124x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x124x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x124x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x124x92x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x124x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x124x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x124x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x124x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x124x92x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x124x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x124x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x124x96x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x124x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x124x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x124x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x124x96x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x124x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x124x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x124x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x1264x1264x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1264x1296x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x127x127x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x127x127x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x127x127x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x127x127x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x127x127x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x127x127x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x127x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x127x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x127x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x127x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x127x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x127x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x127x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x127x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x128x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x128x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x128x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x128x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x128x128x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x512x128x128x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x512x128x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x128x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x512x128x128x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[1]
2x512x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x128x128x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x128x128x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x128x128x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x128x128x1x1x1x1x12288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:82
2x512x128x128x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x512x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x128x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9]
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x128x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x128x128x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x128x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x128x128x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x512x128x128x1x1x1x1x12x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x12x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x12x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x12x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x12x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3]
2x512x128x128x1x1x1x1x256x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x128x128x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[3]
2x512x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2]
2x512x128x128x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x128x128x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x128x128x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x128x128x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x6x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x1x1x1x6x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x2x2x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x128x128x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:129
2x512x128x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x128x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x128x128x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x128x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x128x128x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x128x128x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x128x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x128x1x3x3x1x768x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x128x128x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x128x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x128x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x128x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x128x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x128x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x128x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x128x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x128x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x128x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x128x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x128x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x128x92x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x128x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x128x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x128x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x128x92x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x128x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x128x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x128x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x128x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x128x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x128x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x128x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x1296x1264x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1296x1296x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x129x129x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x129x129x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x129x129x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x129x129x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x12x12x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x12x12x1x3x3x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x12x12x1x3x3x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x12x12x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x12x12x1x3x3x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x12x12x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x12x12x1x3x3x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x12x12x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x12x12x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x12x12x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x12x12x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x130x130x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x131x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x131x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x131x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x131x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x131x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x132x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x132x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x132x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x132x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x132x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x132x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x132x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x132x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x132x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x132x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x132x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x132x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x132x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x132x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x132x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x132x88x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x132x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x132x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x132x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x132x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x132x88x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x132x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x132x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x132x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x132x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x132x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x132x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x132x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x132x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x132x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x132x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x132x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x132x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x132x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x135x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x135x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x135x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x135x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x135x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x136x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x136x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x136x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x136x100x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x136x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x136x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x136x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x136x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x136x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x136x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x136x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x136x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x136x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x136x88x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x136x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x136x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x136x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x136x88x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x136x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x136x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x136x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x136x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x136x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x136x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x136x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x136x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x136x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x136x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x136x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x139x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x139x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x139x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x139x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x139x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x139x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x139x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x139x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x13x13x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x13x13x1x1x1x1x1000x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x1000x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x13x13x1x1x1x1x1000x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x1000x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x1000x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x13x13x1x1x1x1x1000x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x1000x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x13x13x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x13x13x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x64x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x13x13x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x13x13x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x13x13x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x13x13x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x13x13x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x13x13x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x13x13x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x13x13x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x13x13x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x13x13x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x140x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x140x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x140x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x140x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x140x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x140x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x140x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x140x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x140x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x140x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x140x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x140x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x140x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x140x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x140x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x140x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x140x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x140x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x140x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x140x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x140x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x140x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x140x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x140x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x140x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x140x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x140x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x140x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x140x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x140x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x140x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x143x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x143x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x143x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x143x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x143x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x143x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x144x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x144x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x144x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x144x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x144x112x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x144x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x144x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x144x144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x144x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x144x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x144x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x144x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x144x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x144x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x144x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x144x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x144x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x144x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x144x92x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x144x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x144x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x144x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x144x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x144x92x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x144x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x144x96x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x144x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x144x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x144x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x144x96x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x144x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x144x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x144x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x147x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x147x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x147x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x147x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x148x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x148x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x148x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x148x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x148x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x148x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x148x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x148x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x148x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x148x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x148x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x148x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x148x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x148x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x148x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x148x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x148x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x148x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x148x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x148x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x148x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x148x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x1024x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:250
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x1024x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:218
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:208
2x512x14x14x1x1x1x1x1024x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:223
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:228
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:243
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:249
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:213
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:230
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:236
2x512x14x14x1x1x1x1x1024x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;TransposedConvBinWinoRxS<3-2>:249
2x512x14x14x1x1x1x1x1024x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:171
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x14x14x1x1x1x1x1024x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:230
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:239
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:226
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x1024x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x1088x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x112x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x112x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x12288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x14x14x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,254[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,254[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x512x14x14x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x2x2x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x112x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x144x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x2048x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:2
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x14x14x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x14x14x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,6,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[6];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x14x14x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x14x14x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x14x14x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17
2x512x14x14x1x7x7x1x1024x4x3x3x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x14x14x1x7x7x1x512x4x3x3x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x151x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x151x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x151x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x151x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x151x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x1520x1520x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1520x1552x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1520x2715x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1520x2716x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1520x2747x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1520x2748x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x152x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x152x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x152x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x152x100x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x152x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x152x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x152x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x152x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x152x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x152x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x152x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x152x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x152x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x152x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x152x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x152x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x152x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x152x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x152x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x152x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x152x96x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x152x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x152x96x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x152x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x152x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x152x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x1536x1536x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x1536x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x1536x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x1520x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x1552x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x2715x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x2716x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x2747x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1552x2748x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x155x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x155x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x155x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x155x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x156x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x156x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x156x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x156x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x156x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x156x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x156x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x156x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x156x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x156x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x156x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x156x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x156x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x156x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x156x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x156x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x156x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x156x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x156x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x156x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x156x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x156x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x156x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x156x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x156x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x159x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x159x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x159x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x159x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x159x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x159x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x159x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x159x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x159x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x159x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x15x15x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x15x15x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x15x15x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:220
2x512x15x15x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:192
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:101
2x512x15x15x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:104
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x15x15x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x512x15x15x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x15x15x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x15x15x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:242
2x512x15x15x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:236
2x512x15x15x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:238
2x512x15x15x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:232
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x15x15x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:237
2x512x15x15x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:235
2x512x15x15x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:157
2x512x15x15x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:156
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x15x15x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x512x15x15x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x15x15x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x15x15x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x15x15x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:144
2x512x15x15x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:144
2x512x15x15x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x15x15x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:51
2x512x15x15x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:57
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x15x15x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x160x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x160x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x160x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x160x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x160x160x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x160x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x160x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x160x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x160x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x160x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x160x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x160x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x160x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x160x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x160x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x160x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x160x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x160x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x160x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x160x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x160x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x163x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x163x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x163x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x163x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x163x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x163x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x163x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x163x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x164x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x164x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x164x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x164x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x164x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x164x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x164x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x164x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x164x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x164x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x164x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x164x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x164x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x164x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x164x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x164x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x164x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x164x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x164x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x164x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x164x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x164x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x164x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x164x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x167x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x167x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x167x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x167x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x167x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x168x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x168x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x168x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x168x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x168x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x168x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x168x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x168x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x168x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x168x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x168x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x168x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x168x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x168x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x168x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x168x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x168x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x168x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x168x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x168x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x168x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x168x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x168x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x168x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x168x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x168x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x168x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x168x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x168x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x16x16x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x12x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x12x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x6x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[4];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x2x2x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x16x16x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x16x16x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x16x16x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x16x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x16x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x16x16x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x16x16x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x16x16x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x16x16x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x16x16x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x16x16x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x16x16x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x16x16x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x16x16x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x16x16x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x16x16x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x16x16x1x3x3x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x16x16x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x16x16x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x16x16x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x16x16x1x3x3x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x16x16x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x4x0x0x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x16x16x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x16x16x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x16x16x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x16x16x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x16x16x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x16x16x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x16x16x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x16x16x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x16x16x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x512x16x16x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x16x16x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x16x16x1x7x7x1x512x2x3x3x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x512x16x80x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x16x80x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,96[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x16x80x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x16x80x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+4
2x512x16x80x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x16x80x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x16x80x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[8];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x1776x1776x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1776x1776x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1776x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1776x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x17x17x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x17x17x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x17x17x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x17x17x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x17x17x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x17x17x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x17x17x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x17x17x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x17x17x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x17x17x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x17x17x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x17x17x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x17x17x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x17x17x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+8
2x512x17x17x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x17x17x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x1808x1776x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1808x1776x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1808x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1808x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1808x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1808x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1824x2288x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1840x2272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1840x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x18x18x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x18x18x1x3x3x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x18x18x1x3x3x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x18x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x18x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x18x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x18x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x18x18x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x18x18x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x18x18x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x18x18x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x18x18x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x18x18x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x18x18x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x18x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x18x18x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x18x18x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x18x18x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x18x18x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x18x18x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x18x18x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x18x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x18x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x18x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x18x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x18x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x18x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x18x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[4];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x18x82x1x5x5x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x18x82x1x5x5x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x18x82x1x5x5x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+2
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x18x82x1x5x5x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x18x82x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x512x18x82x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x18x82x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x18x82x1x5x5x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x1904x1904x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1904x1904x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1904x1936x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1904x1936x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x192x192x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1936x1904x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1936x1904x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x1936x1936x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x1936x1936x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x19x19x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:240
2x512x19x19x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x512x19x19x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:227
2x512x19x19x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x512x19x19x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:55
2x512x19x19x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:233
2x512x19x19x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:69
2x512x19x19x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x512x19x19x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x19x19x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:253
2x512x19x19x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:212
2x512x19x19x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x19x19x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,4,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:255
2x512x19x19x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:238
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:253
2x512x19x19x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:251
2x512x19x19x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x19x19x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:198
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:198
2x512x19x19x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:251
2x512x19x19x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];TransposedConvBinWinoRxS<3-2>:76
2x512x19x19x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x19x19x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:199
2x512x19x19x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:87
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:81
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];TransposedConvBinWinoRxS<3-2>:160
2x512x19x19x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:251
2x512x19x19x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:230
2x512x19x19x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x19x19x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:224
2x512x19x19x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x19x19x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x486x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x486x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x512x19x19x1x3x3x1x510x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x510x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:249
2x512x19x19x1x3x3x1x510x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:242
2x512x19x19x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:205
2x512x19x19x1x3x3x1x510x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:252
2x512x19x19x1x3x3x1x510x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:73
2x512x19x19x1x3x3x1x510x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:198
2x512x19x19x1x3x3x1x510x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:116
2x512x19x19x1x3x3x1x510x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x19x19x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x510x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:235
2x512x19x19x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x510x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x510x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:227
2x512x19x19x1x3x3x1x510x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:255
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];TransposedConvBinWinoRxS<3-2>:255
2x512x19x19x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:206
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:199
2x512x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];TransposedConvBinWinoRxS<3-2>:83
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];TransposedConvBinWinoRxS<3-2>:91
2x512x19x19x1x3x3x1x512x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x1x100x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x100x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x100x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x100x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x101x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x101x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x101x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x101x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x102x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x102x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x104x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x104x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x104x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x104x1x1x3x1x512x158x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x105x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x105x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x107x1x1x3x1x512x119x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x107x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x107x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x107x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x107x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x107x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x107x1x1x3x1x512x147x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x109x1x1x3x1x512x119x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x109x1x1x3x1x512x119x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x109x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x109x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x109x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x109x1x1x3x1x512x124x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x111x1x1x3x1x512x131x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x111x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x111x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x113x1x1x3x1x512x131x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x113x1x1x3x1x512x131x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x113x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x113x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x113x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x113x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x114x1x1x3x1x512x104x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x115x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x115x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x115x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x116x1x1x3x1x512x104x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x116x1x1x3x1x512x104x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x117x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x117x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x117x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x117x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x117x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x117x1x1x3x1x512x94x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x120x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x121x1x1x3x1x512x105x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x121x1x1x3x1x512x118x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x122x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x122x1x1x3x1x512x114x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x122x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x122x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x123x1x1x3x1x512x100x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x123x1x1x3x1x512x105x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x123x1x1x3x1x512x105x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x123x1x1x3x1x512x118x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x123x1x1x3x1x512x118x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x124x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x124x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x124x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x124x1x1x3x1x512x97x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x125x1x1x3x1x512x100x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x125x1x1x3x1x512x100x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x125x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x125x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x126x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x126x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x127x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x127x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x127x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x127x1x1x3x1x512x90x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x128x1x1x3x1x512x82x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x128x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x128x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x128x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x128x1x1x3x1x512x98x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x130x1x1x3x1x512x82x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x130x1x1x3x1x512x82x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x131x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x131x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x131x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x131x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x133x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x133x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x133x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x133x1x1x3x1x512x86x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x133x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x133x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x133x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x133x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x133x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x133x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x134x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x134x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x134x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x134x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x135x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x135x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x135x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x135x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x135x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x135x1x1x3x1x512x87x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x136x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x136x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x136x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x136x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x136x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x136x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x136x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x136x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x136x1x1x3x1x512x77x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x136x1x1x3x1x512x80x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x137x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x137x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x137x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x137x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x138x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x138x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x138x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x138x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x138x1x1x3x1x512x80x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x138x1x1x3x1x512x80x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x139x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x139x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x139x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x140x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x140x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x140x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x140x1x1x3x1x512x79x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x141x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x141x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x141x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x141x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x141x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x141x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x141x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x141x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x142x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x142x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x143x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x143x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x143x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x143x1x1x3x1x512x73x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x143x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x143x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x144x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x144x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x144x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x144x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x144x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x144x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x144x1x1x3x1x512x72x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x145x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x145x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x145x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x145x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x146x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x146x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x146x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x146x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x146x1x1x3x1x512x67x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x146x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x146x1x1x3x1x512x71x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x147x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x148x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x148x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x148x1x1x3x1x512x66x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x148x1x1x3x1x512x67x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x148x1x1x3x1x512x67x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x148x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x148x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x149x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x149x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x150x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x150x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x150x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x150x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x150x1x1x3x1x512x66x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x150x1x1x3x1x512x66x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x150x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x150x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x150x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x150x1x1x3x1x512x76x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x151x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x152x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x152x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x152x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x152x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x152x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x152x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x153x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x153x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x153x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x153x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x153x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x153x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x154x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x154x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x154x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x154x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x61x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x154x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x154x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x154x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x154x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x154x1x1x3x1x512x74x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x155x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x155x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x155x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x155x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x155x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x155x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x155x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x155x1x1x3x1x512x59x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x155x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x155x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x155x1x1x3x1x512x65x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x156x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x156x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x156x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x156x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x156x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x156x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x156x1x1x3x1x512x70x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x157x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x157x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x157x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x157x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x157x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x157x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x157x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x158x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x158x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x158x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x158x1x1x3x1x512x64x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x158x1x1x3x1x512x70x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x158x1x1x3x1x512x70x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x159x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x159x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x159x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x160x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x160x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x160x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x160x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x161x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x161x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x161x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x161x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x162x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x162x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x162x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x162x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x162x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x162x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x162x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x162x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x162x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x162x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x162x1x1x3x1x512x68x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x163x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x163x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x163x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x163x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x163x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x163x1x1x3x1x512x56x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x163x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x163x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x164x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x164x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x164x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x164x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x164x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x164x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x164x1x1x3x1x512x58x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x165x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x165x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x165x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x165x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x165x1x1x3x1x512x63x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x166x1x1x3x1x512x58x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x166x1x1x3x1x512x58x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x166x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x166x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x167x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x167x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x167x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x167x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x167x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x167x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x167x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x167x1x1x3x1x512x53x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x167x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x167x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x167x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x168x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x168x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x168x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x168x1x1x3x1x512x62x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x169x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x169x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x169x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x169x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x52x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x169x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x169x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x54x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x169x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x169x1x1x3x1x512x60x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x170x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x170x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x171x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x171x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x171x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x171x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x171x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x172x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x172x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x172x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x172x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x173x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x173x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x173x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x173x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x173x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x173x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x173x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x173x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x173x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x173x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x174x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x174x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x174x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x174x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x174x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x175x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x175x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x176x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x176x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x176x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x176x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x176x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x176x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x176x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x176x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x176x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x176x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x177x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x177x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x177x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x177x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x177x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x177x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x178x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x178x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x178x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x178x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x179x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x179x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x179x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x179x1x1x3x1x512x46x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x180x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x180x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x180x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x180x1x1x3x1x512x49x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x180x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x180x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x180x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x180x1x1x3x1x512x51x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x180x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x180x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x182x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x182x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x182x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x182x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x182x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x182x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x182x1x1x3x1x512x55x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x184x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x184x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x184x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x184x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x184x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x184x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x186x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x187x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x187x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x187x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x188x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x188x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x188x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x188x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x188x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x188x1x1x3x1x512x47x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x189x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x189x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x189x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x189x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x189x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x189x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x189x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x189x1x1x3x1x512x48x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x190x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x190x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x190x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x190x1x1x3x1x512x41x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x190x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x190x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x190x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x190x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x190x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x190x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x191x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x191x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x191x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x191x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x192x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x192x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x192x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x192x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x193x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x193x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x193x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x193x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x194x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x194x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x195x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x195x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x195x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x195x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x195x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x195x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x195x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x195x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x195x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x195x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x196x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x196x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x196x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x196x1x1x3x1x512x44x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x197x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x197x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x197x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x197x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x197x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x197x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x199x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x199x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x199x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x1x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+8
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 1, 1, 1>+16
2x512x1x1x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 8, 1, 1>+32
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 8, 1, 1>+32
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,104;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+64
2x512x1x1x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+64
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x1x1x1x4x4x1x100x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x4x4x1x100x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x4x4x1x100x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,6,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x4x4x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x1x1x1x4x4x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x1x1x1x4x4x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x1x1x1x7x7x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x7x7x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x7x7x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x7x7x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x7x7x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x7x7x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x1x1x7x7x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x1x1x1x7x7x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x1x200x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x200x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x201x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x201x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x201x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x201x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x201x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x201x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x201x1x1x3x1x512x45x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x202x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x202x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x202x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x202x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x202x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x202x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x203x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x203x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x203x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x203x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x203x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x204x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x204x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x204x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x204x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x204x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x204x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x205x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x205x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x205x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x205x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x205x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x205x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x205x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x205x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x206x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x206x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x206x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x206x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x207x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x207x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x207x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x207x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x207x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x207x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x207x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x207x1x1x3x1x512x43x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x208x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x208x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x208x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x208x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x208x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x208x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x210x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x210x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x210x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x210x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x210x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x210x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x210x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x210x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x210x1x1x3x1x512x37x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x211x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x211x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x212x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x212x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x212x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x212x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x213x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x213x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x213x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x213x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x213x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x213x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x215x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x215x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x215x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x215x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x215x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x215x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x217x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x217x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x217x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x217x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x218x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x218x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x218x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x218x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x220x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x220x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x220x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x220x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x220x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x220x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x220x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x220x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x220x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x220x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x220x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x220x1x1x3x1x512x39x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x221x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x221x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x222x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x222x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x222x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x222x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x222x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x222x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x222x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x222x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x222x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x222x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x223x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x223x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x223x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x223x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x223x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x223x1x1x3x1x512x38x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x224x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x224x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x224x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x224x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x224x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x224x1x1x3x1x512x32x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x225x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x226x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x227x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x227x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x227x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x227x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x227x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x227x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x228x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x228x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x228x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x228x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x229x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x229x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x229x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x229x1x1x3x1x512x33x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x230x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x230x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x232x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x232x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x232x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x232x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x233x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x233x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x234x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x234x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x235x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x235x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x235x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x235x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x235x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x235x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x236x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x236x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x236x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x236x1x1x3x1x512x30x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x237x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x237x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x237x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x237x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x237x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x237x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x238x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x238x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x239x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x239x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x239x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x239x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x239x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x239x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x240x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x240x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x240x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x240x1x1x3x1x512x29x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x241x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x241x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x241x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x241x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x241x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x241x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x241x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x241x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x243x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x243x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x243x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x243x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x243x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x243x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x243x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x243x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x246x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x246x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x247x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x247x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x248x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x248x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x248x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x248x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x248x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x248x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x249x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x249x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x249x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x249x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x250x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x250x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x250x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x250x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x250x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x250x1x1x3x1x512x31x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x251x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x251x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x252x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x252x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x252x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x252x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x253x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x253x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x253x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x253x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x253x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x253x1x1x3x1x512x27x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x253x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x253x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x254x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x254x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x255x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x255x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x255x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x255x1x1x3x1x512x24x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x255x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x255x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x255x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x255x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x255x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x255x1x1x3x1x512x28x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x256x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x256x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x256x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x256x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x257x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x257x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x257x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x257x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x257x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x257x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x259x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x259x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x259x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x259x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x260x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x260x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x260x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x260x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x262x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x262x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x262x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x262x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x262x1x1x3x1x512x25x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x264x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x264x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x264x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x264x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x264x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x264x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x266x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x266x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x266x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x266x1x1x3x1x512x26x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x267x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x267x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x269x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x271x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x272x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x272x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x273x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x273x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x273x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x273x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x274x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x274x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x274x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x276x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x276x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x276x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x276x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x276x1x1x3x1x512x23x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x278x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x278x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x278x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x278x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x279x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x281x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x281x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x282x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x282x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x284x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x284x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x284x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x284x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x285x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x285x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x287x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x287x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x287x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x287x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x288x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x289x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x290x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x290x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x291x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x291x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x291x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x291x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x293x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x293x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x293x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x293x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x296x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x296x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x298x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x298x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x298x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x298x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x304x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x304x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x305x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x305x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x305x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x306x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x306x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x306x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x306x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x307x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x307x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x307x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x307x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x307x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x307x1x1x3x1x512x20x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x310x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x310x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x311x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x311x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x312x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x312x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x312x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x312x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x313x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x313x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x313x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x313x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x314x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x314x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x315x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x315x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x316x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x316x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x316x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x316x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x317x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x317x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x317x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x317x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x320x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x320x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x320x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x320x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x321x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x321x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x321x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x321x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x322x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x322x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x322x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x322x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x322x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x322x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x512x1x322x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x322x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x323x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x323x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x323x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x323x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x323x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x323x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x323x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x323x1x1x3x1x512x18x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x324x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x324x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x326x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x326x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x326x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x326x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x327x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x327x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x329x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x329x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x329x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x329x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x329x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x329x1x1x3x1x512x15x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x330x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x331x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x331x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x331x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x331x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x332x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x332x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x332x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x332x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x334x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x334x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x334x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x334x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x336x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x336x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x336x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x336x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x337x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x337x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x337x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x337x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x338x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x338x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x338x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x338x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x338x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x338x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x338x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x338x1x1x3x1x512x17x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x339x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x339x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x339x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x339x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x339x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x339x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x339x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x339x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x346x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x348x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x348x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x349x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x349x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x34x1x1x3x1x512x329x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x351x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x351x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x351x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x351x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x353x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x353x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x355x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x355x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x355x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x355x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x357x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x357x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x359x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x359x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x359x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x359x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x360x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x360x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x361x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x361x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x361x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x362x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x362x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x362x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x362x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x363x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x363x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x363x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x363x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x363x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x363x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x363x1x1x3x1x512x19x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x365x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x365x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x365x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x365x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x367x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x367x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x367x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x367x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x368x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x36x1x1x3x1x512x329x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x36x1x1x3x1x512x329x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x370x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x370x1x1x3x1x512x13x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x372x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x374x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x374x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x375x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x377x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x377x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x379x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x379x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x381x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x381x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x381x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x381x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x381x1x1x3x1x512x12x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x383x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x383x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x383x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x384x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x385x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x385x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x512x1x386x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x386x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x392x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x394x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x394x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x401x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x403x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x403x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x512x1x406x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x408x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x408x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x408x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x40x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x40x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x410x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x410x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x415x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x415x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x416x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x417x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x417x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x417x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x417x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x418x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x418x1x1x3x1x512x11x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x419x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x421x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x421x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x427x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x427x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x427x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x429x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x429x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x429x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x429x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x429x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x429x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x42x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x42x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x42x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x42x1x1x3x1x512x418x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x436x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x436x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x436x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x438x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x438x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x438x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x438x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x438x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x438x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x453x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x453x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x454x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x455x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x455x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x455x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x455x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x456x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x456x1x1x3x1x512x10x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x458x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x458x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x45x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x45x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x460x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x460x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x460x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x460x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x462x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x462x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x463x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x464x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x464x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x464x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x464x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x465x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x465x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x465x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x465x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x467x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x467x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x467x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x467x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x468x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x468x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x470x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x470x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x470x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x470x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x470x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x472x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x472x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x472x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x472x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x472x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x474x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x474x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x474x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x474x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x512x1x474x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x474x1x1x3x1x512x9x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x47x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x47x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x47x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x47x1x1x3x1x512x543x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x485x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x486x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x486x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x487x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x487x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x487x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x488x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x488x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x488x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x488x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x489x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x489x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x490x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x491x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x492x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x492x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x512x1x493x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x493x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x493x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x494x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x495x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x495x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x496x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x496x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x497x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x499x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x499x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x500x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x502x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x502x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x526x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x528x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x528x1x1x3x1x512x7x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x52x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x52x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x531x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x531x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x533x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x533x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x533x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x533x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x537x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x537x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x539x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x539x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x539x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x539x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x54x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x54x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x54x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x54x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x54x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x54x1x1x3x1x512x440x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x568x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x568x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x56x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x56x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x56x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x56x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x56x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x56x1x1x3x1x512x397x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x570x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x570x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x570x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x570x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x58x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x58x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x58x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x58x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x590x1x1x3x1x512x6x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x592x1x1x3x1x512x6x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x592x1x1x3x1x512x6x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x60x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x60x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x615x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x615x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x617x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x617x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x617x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x617x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x61x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x61x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x622x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x622x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x624x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x624x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x624x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x624x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x62x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x62x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x62x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x62x1x1x3x1x512x294x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x633x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x633x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x635x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x635x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x635x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x635x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x63x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x63x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x63x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x63x1x1x3x1x512x274x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x65x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x65x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x671x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x671x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x673x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x673x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x673x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x673x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x67x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x67x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x67x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x67x1x1x3x1x512x299x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x680x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x680x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x682x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x682x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+16
2x512x1x682x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x682x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x688x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x688x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x68x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x68x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x690x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x690x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x690x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x690x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x70x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x70x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x70x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x70x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x70x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x70x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x721x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x721x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x721x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x721x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x723x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x723x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x723x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x723x1x1x3x1x512x3x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x723x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x723x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x723x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x723x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x72x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x72x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x72x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x72x1x1x3x1x512x291x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x731x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x731x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x733x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x733x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x733x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x733x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x747x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x747x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x749x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x749x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x749x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x749x1x1x3x1x512x4x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x512x1x76x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x76x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x77x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x77x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x78x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x78x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x78x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x78x1x1x3x1x512x222x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x78x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x78x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x79x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x79x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x79x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x79x1x1x3x1x512x253x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x80x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x80x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x80x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x80x1x1x3x1x512x224x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x81x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x81x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x83x1x1x3x1x512x116x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x83x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x83x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x83x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x83x1x1x3x1x512x199x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x85x1x1x3x1x512x116x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x85x1x1x3x1x512x116x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x85x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x85x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x85x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x85x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x87x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x87x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x87x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x87x1x1x3x1x512x181x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x87x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x87x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x87x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x1x87x1x1x3x1x512x189x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x88x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x88x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x90x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x90x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x90x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x90x1x1x3x1x512x155x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x91x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x91x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x93x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x93x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+32
2x512x1x93x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x93x1x1x3x1x512x150x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x96x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x96x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x96x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x96x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x98x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x98x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x512x1x98x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x98x1x1x3x1x512x143x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x98x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x98x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x98x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x1x98x1x1x3x1x512x171x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x1x98x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x98x1x1x3x1x512x172x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x1x99x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x99x1x1x3x1x512x170x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x2024x2024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2024x2024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2024x2056x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2024x2056x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2031x2031x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2031x2031x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2031x2063x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2031x2063x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2032x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2032x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2032x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2032x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2032x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2032x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2064x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2064x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2064x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2064x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2032x2064x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2032x2064x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2033x2033x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2033x2033x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2033x2065x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2033x2065x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x2048x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x2048x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x2048x2048x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x2048x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x2048x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x512x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2056x2024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2056x2024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2056x2056x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2056x2056x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2063x2031x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2063x2031x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2063x2063x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2063x2063x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2032x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2032x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2032x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2032x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2032x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2032x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2064x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2064x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2064x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2064x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2064x2064x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2064x2064x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2065x2033x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2065x2033x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2065x2065x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x2065x2065x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x20x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x20x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x20x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x20x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x20x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x20x20x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x20x20x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x20x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x20x20x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x20x20x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x20x20x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x20x20x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x20x20x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x20x20x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x20x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x20x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x20x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x20x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x20x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x20x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x27x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x20x27x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x27x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x20x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x20x27x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x27x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x27x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x20x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x20x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x20x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x20x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x20x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x20x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x20x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x20x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x20x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x20x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x20x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x20x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x20x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x20x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x20x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x20x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x20x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x20x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x20x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x20x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x20x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x20x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x20x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x20x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x20x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x20x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x20x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x20x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x20x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x20x84x1x5x5x1x256x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x512x20x84x1x5x5x1x256x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x20x84x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x20x84x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x84x1x5x5x1x256x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x20x84x1x5x5x1x256x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x20x84x1x5x5x1x256x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x20x84x1x5x5x1x256x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x20x84x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x20x84x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x20x84x1x5x5x1x256x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+4
2x512x20x84x1x5x5x1x256x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x218x218x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,241[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x218x218x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x218x218x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+16
2x512x21x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x21x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x21x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x21x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x21x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x26x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x21x26x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x21x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x26x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x21x26x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x26x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x26x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x26x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x26x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x21x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x21x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x21x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x21x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x21x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x21x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x21x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,4,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x21x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x21x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x21x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x21x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x21x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x21x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x21x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x21x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x21x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x21x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x21x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x21x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x21x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x21x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x21x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x21x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x21x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x21x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x21x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x21x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x21x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x21x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x21x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x21x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x21x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x21x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x21x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x21x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x21x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x21x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x21x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x21x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x220x220x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x220x220x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x220x220x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x512x222x222x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x222x222x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x222x222x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x512x223x223x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x223x223x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x223x223x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x223x223x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x224x224x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x224x224x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x224x224x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x224x224x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x224x224x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x224x224x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x224x224x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x224x224x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x224x224x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x224x224x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x225x225x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x225x225x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x225x225x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x225x225x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x225x225x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x225x225x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x2272x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2272x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2288x1824x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2288x2320x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x22x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x22x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x22x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x22x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x22x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x22x22x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x22x22x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x22x22x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+4
2x512x22x22x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x22x22x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x22x22x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x22x22x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x22x22x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x22x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x22x22x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x22x22x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x22x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+2
2x512x22x22x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x22x22x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x22x22x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x22x22x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x22x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x22x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x22x22x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x22x22x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x22x22x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+1
2x512x22x22x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x22x22x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x22x22x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x22x22x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x512x22x22x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x22x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x22x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x22x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x22x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x22x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x22x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x22x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x22x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x22x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x22x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x22x30x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x22x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x22x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x22x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x22x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x22x33x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x22x33x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x33x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x22x33x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x22x33x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x22x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x33x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x33x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x22x33x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x22x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x22x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x22x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x22x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x22x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x22x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x22x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x22x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x22x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x22x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x22x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x22x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x22x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x22x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x22x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x22x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x22x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x22x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x22x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x22x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x22x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x22x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x22x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x22x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x22x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x22x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x22x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x22x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x22x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x22x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x22x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x22x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x22x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x2304x1808x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x1840x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2320x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2320x2320x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x23x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x23x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x23x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x23x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x23x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x23x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x23x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x23x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x23x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x23x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x23x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x23x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x23x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x23x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x23x31x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x31x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x23x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x31x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x23x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x23x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x23x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x23x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x23x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x23x35x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x35x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x35x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x35x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x35x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x23x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x23x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x35x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x23x35x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x35x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x23x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x23x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x23x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x23x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x23x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x23x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x23x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x23x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x23x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x37x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x23x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x23x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x39x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x23x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x23x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x23x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x23x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x23x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x23x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x23x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x23x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x23x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x23x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x23x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x23x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x23x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x23x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x23x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x23x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x23x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x23x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x240x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x240x240x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x240x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x240x272x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x24x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x24x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x24x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x24x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x24x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x24x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x24x1x2x2x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x24x24x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x24x24x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x24x24x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x24x24x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x24x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x24x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x26x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x26x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x24x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x24x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x24x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x24x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x24x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x24x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x24x29x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x24x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x24x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x24x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x31x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x24x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x24x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x24x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x24x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x24x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x24x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x24x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x24x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x34x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x24x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x24x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x24x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x35x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x24x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x36x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x24x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x36x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x24x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x36x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x24x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x36x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x37x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x24x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x37x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x37x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x24x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x24x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x24x39x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x24x39x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x24x39x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x24x39x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x39x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x24x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x39x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x39x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x24x39x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x40x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x24x40x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x40x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x24x40x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x40x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x40x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x40x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x24x40x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x24x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x24x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x24x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x41x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x42x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x24x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x24x42x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x24x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x24x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x24x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x24x42x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x24x48x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x24x48x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x2560x2560x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2560x2560x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x256x256x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x1x1x1x12x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, OddC, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Default, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x12x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x1536x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x256x256x1x1x1x1x312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x624x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x1x1x1x6x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x256x256x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x256x256x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138
2x512x256x256x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x256x256x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x256x256x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x256x256x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x256x256x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x256x256x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x256x256x1x3x3x1x512x4x2x2x0x2x2x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x256x256x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x256x256x1x9x9x1x512x4x4x4x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x257x257x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x25x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x25x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x25x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x25x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x25x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x25x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x25x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x25x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x25x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x25x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,3,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x25x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x25x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x25x25x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x25x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x25x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x25x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x25x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x25x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x25x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x27x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x25x27x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x25x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x25x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x25x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x29x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x25x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x30x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x25x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x25x31x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x25x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x25x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x25x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x33x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x25x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x33x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x33x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x25x34x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x34x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x34x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x34x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x34x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x25x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x25x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x25x34x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x34x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x34x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x34x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x25x35x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x25x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x25x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x35x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x25x36x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x37x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x37x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x38x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x25x38x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x38x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x38x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x38x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x38x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x38x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x25x38x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x25x38x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x25x38x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x25x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x38x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x25x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x39x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x39x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x40x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x25x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x25x40x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x25x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x25x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x25x41x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x25x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x41x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x25x41x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x25x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x25x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x25x41x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x25x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x25x42x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x25x42x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x26x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x26x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x26x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x26x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x26x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x26x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x26x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x26x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x26x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x26x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x26x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x26x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x26x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x26x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x26x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x26x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x26x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x26x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x26x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x26x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x26x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x26x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x26x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x26x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x26x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x26x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x26x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x26x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x26x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x26x26x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x26x26x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x26x26x1x3x3x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x26x26x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x26x26x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x26x26x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x26x26x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x26x26x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x26x26x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x26x26x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x26x26x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x26x26x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x26x26x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x26x26x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x26x26x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x26x26x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x26x26x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x26x26x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x26x26x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x26x26x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x26x26x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x26x26x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x26x26x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x26x26x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x26x26x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x26x26x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x26x26x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x26x26x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x26x26x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x26x26x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x26x26x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x26x26x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x26x26x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x26x26x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x272x240x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x272x240x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x272x272x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x272x272x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x2731x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2731x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x2732x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x2732x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x27x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x27x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x27x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x27x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x27x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x27x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x27x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x27x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x27x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x27x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x27x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x27x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x27x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x27x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x27x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x27x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x27x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x27x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x27x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x27x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x27x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x27x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x27x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x27x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x27x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x27x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x27x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x27x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x27x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x27x27x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x27x27x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x27x27x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x27x27x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x27x27x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x27x27x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x27x27x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x27x27x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x27x27x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x27x27x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x27x27x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x27x27x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x27x27x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x27x27x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x27x27x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x28x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x28x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x28x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x11x11x1x512x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,0,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,2;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:238
2x512x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6]
2x512x28x28x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:216
2x512x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:213
2x512x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x1024x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:209
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:200
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x512x28x28x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x1024x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:230
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:248
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:230
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x1024x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x1029x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:64
2x512x28x28x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:80
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:235
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:129
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:71;TransposedConvBinWinoRxS<3-2>:72
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:205
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:72;TransposedConvBinWinoRxS<3-2>:65
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];TransposedConvBinWinoRxS<3-2>:192
2x512x28x28x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:85
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:236
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:204
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:99;TransposedConvBinWinoRxS<3-2>:72
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];TransposedConvBinWinoRxS<2-3>:69;TransposedConvBinWinoRxS<3-2>:91
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x128x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:241
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:243
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:65
2x512x28x28x1x1x1x1x128x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];TransposedConvBinWinoRxS<2-3>:90;TransposedConvBinWinoRxS<3-2>:94
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];TransposedConvBinWinoRxS<2-3>:65;TransposedConvBinWinoRxS<3-2>:64
2x512x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:93;TransposedConvBinWinoRxS<3-2>:93
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:248
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:93;TransposedConvBinWinoRxS<3-2>:80
2x512x28x28x1x1x1x1x128x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:85;TransposedConvBinWinoRxS<3-2>:93
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:212
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:209
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:73;TransposedConvBinWinoRxS<3-2>:76
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:69;TransposedConvBinWinoRxS<3-2>:84
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:224
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:76
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:229
2x512x28x28x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:64
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[5];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;TransposedConvBinWinoRxS<3-2>:243
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:94;TransposedConvBinWinoRxS<3-2>:81
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x128x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];TransposedConvBinWinoRxS<2-3>:80;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:249
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:99;TransposedConvBinWinoRxS<3-2>:80
2x512x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];TransposedConvBinWinoRxS<2-3>:80;TransposedConvBinWinoRxS<3-2>:120
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:214
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];TransposedConvBinWinoRxS<2-3>:66;TransposedConvBinWinoRxS<3-2>:65
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:215
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:64
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x128x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:80
2x512x28x28x1x1x1x1x128x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:64;TransposedConvBinWinoRxS<3-2>:83
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:218
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:212
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:70;TransposedConvBinWinoRxS<3-2>:69
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:73;TransposedConvBinWinoRxS<3-2>:68
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:131
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:130
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:70;TransposedConvBinWinoRxS<3-2>:75
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];TransposedConvBinWinoRxS<2-3>:68;TransposedConvBinWinoRxS<3-2>:71
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x28x28x1x1x1x1x128x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x28x28x1x1x1x1x1536x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Filter1x1Stride1Pad0, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+64
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7]
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7
2x512x28x28x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x512x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:253
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x256x15x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:202
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:206
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:200
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,134[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:250
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x28x28x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:207
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:201
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:239
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:229
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x28x28x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:253
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x256x35x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x512x28x28x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x256x408x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x512x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x512x28x28x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:255
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:233
2x512x28x28x1x1x1x1x256x51x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x28x28x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x512x28x28x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:254
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x512x28x28x1x1x1x1x256x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:235
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:229
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:251
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:229
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x28x28x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:206
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:202
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;TransposedConvBinWinoRxS<3-2>:230
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:200
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x512x28x28x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,68[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x96x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x28x28x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x512x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x28x28x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x768x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x1x3x1x128x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x1x3x1x512x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x1x5x1x128x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x512x28x28x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:197
2x512x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x1x7x1x512x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x1x1x128x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x28x28x1x3x3x1x256x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x28x28x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x28x28x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x16x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x256x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 4, 2, 1, 4, 4, 4, 2, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x2x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x3x3x1x512x2x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x32x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x28x28x1x3x3x1x512x4x2x2x0x2x2x0x2x2x0x0x32xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x4x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x28x28x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x512x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x8x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x28x28x1x3x3x1x512x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x28x28x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x3x5x1x128x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x3x7x1x128x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x28x28x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x28x28x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x5x1x1x128x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x28x28x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,66;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x28x28x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x28x28x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x28x28x1x7x1x1x512x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x28x28x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x28x28x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,76;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+64
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x28x28x1x9x9x1x512x1x4x4x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x29x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x29x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x29x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x29x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x29x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x29x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x29x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x29x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x29x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x29x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x29x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x29x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x29x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x29x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x29x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x29x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x29x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x29x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x29x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x29x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x29x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x29x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x29x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x29x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x29x29x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x29x29x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x29x29x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x29x29x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x29x29x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x29x29x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x29x29x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x29x29x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x29x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x29x29x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+4
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x29x29x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x29x29x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+16
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x29x29x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+64
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+32
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8, 2>+-1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x512x29x29x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+8
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+64
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x29x29x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x29x29x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x512x29x29x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4, 2>+16
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+16
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x29x29x1x4x4x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x29x29x1x6x6x1x512x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256
2x512x2x2x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x30x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x30x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x30x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x30x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x30x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x30x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x30x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x30x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x30x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x30x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x30x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x30x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x30x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x30x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x30x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x30x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x30x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x30x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x30x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x30x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x30x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x30x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x30x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x30x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x30x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x30x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x30x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x30x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x30x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x30x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x30x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x30x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x30x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x30x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x30x30x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x30x30x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x30x30x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x30x30x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x30x30x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x30x30x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x30x30x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x30x30x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x30x30x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x30x30x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x30x30x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x512x30x30x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x30x30x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x30x30x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x31x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x31x20x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x31x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x31x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x31x20x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x31x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,1,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,60[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x31x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x31x20x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x31x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x31x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x31x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x31x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x31x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x31x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x31x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x31x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x31x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x31x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x31x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x31x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x31x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x31x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x31x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x31x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x31x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x31x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x31x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x31x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x31x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x31x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x31x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x31x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x31x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x31x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x31x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x31x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x31x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x31x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x31x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x31x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x31x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x31x31x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x31x31x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x31x31x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x31x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x31x31x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x31x31x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x31x31x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x31x31x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x31x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x31x31x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x31x31x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x31x31x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x31x31x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x31x31x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x31x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x31x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x31x31x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x31x31x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x31x31x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x31x31x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x32x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x32x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x32x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x32x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x32x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x32x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x32x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x32x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x32x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x32x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x32x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x32x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x32x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x32x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x32x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x32x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x32x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x32x32x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x32x32x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x32x32x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x32x32x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x32x32x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9]
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x32x32x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x32x32x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x32x32x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x32x32x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x12x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x12x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x12x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x32x32x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x32x32x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Filter1x1Stride1Pad0, 4, 2, 4, 4, 2, 4, 4, 1, 1, 4>+16
2x512x32x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x32x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:205
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x32x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x32x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x32x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x320x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x1x1x1x320x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x32x32x1x1x1x1x6x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x6x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x32x32x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x32x32x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x32x32x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x32x32x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x32x32x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x32x32x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x32x32x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x32x32x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x32x32x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[3];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x32x32x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x32x32x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x32x32x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x32x32x1x3x3x1x512x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x512x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x32x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x32x32x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x32x32x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x32x32x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+32
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x32x32x1x3x3x1x512x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x32x32x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x32x32x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x512x32x32x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x32x32x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x32x32x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x32x32x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x32x32x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x32x32x1x7x7x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x32x32x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x33x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x33x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x33x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x33x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x33x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x33x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x33x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x33x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x33x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x33x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x33x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x33x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x33x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x33x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x33x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x33x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x33x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x33x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x33x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x33x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x33x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x33x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x33x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x33x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x33x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x33x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x33x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x33x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x33x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x33x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x33x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x33x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x33x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x34x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x34x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x34x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x34x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x34x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x34x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x34x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x34x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x34x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x34x22x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x34x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x34x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x34x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x34x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x22x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x34x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x34x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x34x22x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x34x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x34x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x34x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x34x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x34x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x34x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x34x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x34x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x34x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x34x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x34x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x34x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x34x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x34x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x34x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x34x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x34x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x34x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x34x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x34x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x34x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x34x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x34x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x34x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x34x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x34x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x34x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x34x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x35x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x35x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x35x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x35x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x35x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x35x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x35x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x35x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x35x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x35x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x35x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x35x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x35x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x35x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x35x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x35x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x35x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x35x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x35x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x35x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x35x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x35x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x35x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x35x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x35x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x35x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x35x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x35x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x35x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x35x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x35x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x35x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x35x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x3648x4576x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x3648x4576x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x36x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x36x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x36x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x36x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x36x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x36x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x36x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x36x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x36x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x36x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x36x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x36x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x36x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x36x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x36x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x36x23x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x36x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x36x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x36x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x36x23x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x36x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x36x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x36x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x36x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x36x23x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x36x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x36x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x36x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x36x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x36x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x36x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x36x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x36x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x36x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x36x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x36x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x36x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x36x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x36x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x36x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x36x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x36x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x36x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x36x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x36x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x36x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x36x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x36x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x37x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x37x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x37x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x37x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x37x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x37x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x37x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x37x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x37x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x37x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x37x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x37x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x37x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x37x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x37x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x37x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x38x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x38x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x38x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x38x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x38x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x38x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x38x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x38x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x38x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x38x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x38x24x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x38x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x38x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x38x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x38x24x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x38x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x38x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x38x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x38x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x38x24x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x38x25x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x38x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x38x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x38x25x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x38x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x38x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x38x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x38x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x38x25x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x38x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x38x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x38x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x38x38x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x399x543x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x399x543x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x399x607x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x399x607x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x39x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x39x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x39x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x39x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x39x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x39x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x39x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x39x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x39x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x39x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x39x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x39x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x39x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x39x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x39x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x39x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x39x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x39x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x39x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x39x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x39x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x39x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x39x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x39x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x39x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x39x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x3x3x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x3x3x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x3x3x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x400x544x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x400x544x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x400x544x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x400x544x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x400x608x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4095x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x4096x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x4096x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x4097x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x4097x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x40x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x40x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x40x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x40x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x40x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x40x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x40x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x40x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x40x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x40x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x40x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x40x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x40x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x40x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x40x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x40x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x40x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x40x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x40x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x40x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x40x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x40x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x40x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x40x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x41x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x41x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x41x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x41x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x41x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x41x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x41x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x41x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x41x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x41x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x41x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x41x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x41x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x41x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x41x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x41x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x41x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x512x41x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x41x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x41x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x41x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x41x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x41x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x41x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x42x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x20x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x42x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x42x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x42x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x42x20x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x42x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x42x21x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x21x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x42x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x42x21x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x42x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x42x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x42x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x42x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x42x21x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x42x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x42x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x42x21x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x42x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x42x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x42x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x42x22x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x42x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x23x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x42x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x23x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x42x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x42x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x42x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x42x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x42x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x42x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x42x24x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x42x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x42x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x42x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x42x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x42x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x42x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x42x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x42x25x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x42x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x42x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x42x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x447x399x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x447x399x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x448x400x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x448x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x448x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x448x400x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4576x3648x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x4576x3648x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x512x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x48x48x1x2x2x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x48x48x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x48x48x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x48x48x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x48x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x48x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x48x48x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x512x48x48x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x48x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x48x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x496x496x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x496x528x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x49x49x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x49x49x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x49x49x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x49x49x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x4x16384x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x4x16x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x16x1x1x1x1x1025x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x4x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x196x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x256x1x1x1x1x1025x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x4x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x4x4x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,227[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,80[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x512x4x4x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x16x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+2
2x512x4x4x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x4x4x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 4, 1, 1, 1>+8
2x512x4x4x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,44;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x4x4x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4x4x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x4x4x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x4x4x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x4x4x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x4x4x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x4x4x1x1x1x1x2048x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x4x4x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x4x4x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,5,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+16
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[4];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+16
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,120;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+64
2x512x4x4x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,26;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x4x4x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>+64
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x4x4x1x3x3x1x512x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x4x4x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x4x4x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x4x4x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x4x4x1x4x4x1x100x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x4x4x1x100x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x4x4x1x100x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x4x4x1x100x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x4x4x1x100x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,6,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x4x1x4x4x1x100x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x4x4x1x4x4x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,4,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,63[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x4x4x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x4x4x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4x4x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x4x4x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x4x4x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x4x4x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x4x9x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x4x9x1x1x1x1x1025x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x4x9x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x50x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x511x511x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x511x511x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x511x511x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x511x511x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x511x511x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x512x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:240
2x512x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x512x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:239
2x512x512x512x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:238
2x512x512x512x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x512x512x1x1x1x1x1024x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:256
2x512x512x512x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x512x512x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+32
2x512x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x512x512x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x512x512x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x512x512x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,7[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+128
2x512x512x512x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+32
2x512x512x512x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x512x512x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x512x512x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+32
2x512x512x512x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x512x512x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+32
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+16
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,8,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+64
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[9]
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x512x512x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x512x512x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x512x512x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256
2x512x512x512x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x512x512x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:238
2x512x512x512x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x512x512x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x512x512x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x512x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x51x51x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x528x496x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x528x528x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x53x53x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x53x53x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x53x53x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x53x53x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x53x53x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x53x53x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x53x53x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x53x53x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x53x53x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x53x53x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x53x53x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x55x55x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x55x55x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4]
2x512x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,8,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[8]
2x512x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+32
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+128
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,185[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:187;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x512x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad_MergedGroups<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4, 2>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x256x1x16x16x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x512x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,141[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x256x1x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x256x1x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x256x1x8x8x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x56x56x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x512x56x56x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x42x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x43x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x1024x1x2x2x0x1x1x0x1x1x0x0x16xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x5x5x1x256x1x16x16x0x1x1x0x8x8x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x56x56x1x5x5x1x256x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:10
2x512x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x5x5x1x256x1x32x32x0x1x1x0x16x16x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x5x5x1x256x1x4x4x0x1x1x0x2x2x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x5x5x1x256x1x8x8x0x1x1x0x4x4x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,5,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[5];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x56x56x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x8xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[6];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,128,16,32,32,2,2,1,2,2,0,0,1,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,1[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x57x57x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+128
2x512x57x57x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+32
2x512x57x57x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x57x57x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+128
2x512x57x57x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+8
2x512x57x57x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x57x57x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x57x57x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x57x57x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x57x57x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x512x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x57x57x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+16
2x512x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x58x58x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x58x58x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x58x58x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x58x58x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x58x58x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x58x58x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x58x58x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x58x58x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x58x58x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x58x58x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x58x58x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,267[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+8
2x512x58x58x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+8
2x512x58x58x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x512x59x59x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x59x59x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+128
2x512x59x59x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x59x59x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x59x59x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>+128
2x512x59x59x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x59x59x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x59x59x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x59x59x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x59x59x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x59x59x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x59x59x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x59x59x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+32
2x512x59x59x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x59x59x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x512x59x59x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+16
2x512x5x5x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x5x5x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x5x5x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x5x5x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x5x5x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x5x5x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:138
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:131
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];TransposedConvBinWinoRxS<3-2>:120
2x512x5x5x1x3x3x1x256x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:130
2x512x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x5x5x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[4];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];TransposedConvBinWinoRxS<3-2>:30
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:133
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];TransposedConvBinWinoRxS<3-2>:25
2x512x5x5x1x3x3x1x256x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:151
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];TransposedConvBinWinoRxS<3-2>:13
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:130
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];TransposedConvBinWinoRxS<3-2>:10
2x512x5x5x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:145
2x512x5x5x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x5x5x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x5x5x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x5x5x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x5x5x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x5x5x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x5x5x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x5x5x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x5x5x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x5x5x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x5x5x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x3x3x1x512x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x5x5x1x3x3x1x512x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x5x5x1x3x3x1x512x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x5x5x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x5x5x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x5x5x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x5x5x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x5x5x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x5x5x1x4x4x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x5x5x1x4x4x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x5x5x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x5x5x1x4x4x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x60x60x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x60x60x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x60x60x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x60x60x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x60x60x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x60x60x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x60x60x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+8
2x512x61x61x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x61x61x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x61x61x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x61x61x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x61x61x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x61x61x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x61x61x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x62x62x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x62x62x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x62x62x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x64x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x64x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x64x64x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x64x64x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x64x64x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x64x64x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x12x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x12x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x64x64x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x512x64x64x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x64x64x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x1x1x1x6x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x6x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,218[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x6x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x2x2x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x64x64x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x64x64x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,235[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x64x64x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x64x64x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:128
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x64x64x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x64x64x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x64x64x1x3x3x1x500x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x500x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x502x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x64x64x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x512x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x64x64x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x64x64x1x3x3x1x8x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,193[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x3x3x1x8x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x5x5x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,207[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x64x64x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[4];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x64x64x1x7x7x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x64x64x1x7x7x1x512x1x3x3x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x64x64x1x7x7x1x512x1x9x9x0x1x1x0x3x3x0x0x512xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x65x65x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x66x66x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x6x6x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x6x6x1x3x3x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x6x6x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,4,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[4];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x512x6x6x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x6x6x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x6x6x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x6x6x1x3x3x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x512x6x6x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x6x6x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x6x6x1x3x3x1x512x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x6x6x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x6x6x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x50x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x6x6x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x6x8x1x3x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x72x168x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x72x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x72x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x72x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x72x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x72x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x72x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x752x752x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x752x784x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x75x75x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x75x75x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x75x75x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x75x75x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x75x75x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x75x75x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x75x75x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x75x75x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x75x75x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x75x75x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x75x75x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x75x75x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x75x75x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x75x75x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x75x75x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,5,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x75x75x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x75x75x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x75x75x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x75x75x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x75x75x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x75x75x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x75x75x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x75x75x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x75x75x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x75x75x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x768x768x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x768x768x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x768x768x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x512x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x768x768x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x512x768x768x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1]
2x512x768x768x1x5x5x1x512x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:253
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,4,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,6,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x76x76x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x76x76x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x76x76x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x76x76x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
2x512x76x76x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x76x76x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x76x76x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x76x76x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x76x76x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,10,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[10]
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x77x77x1x3x3x1x256x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,3,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x77x77x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x77x77x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x77x77x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x77x77x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x77x77x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x77x77x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x77x77x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x512x77x77x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9]
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x77x77x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x784x752x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x784x784x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x79x103x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x103x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x107x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x123x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x123x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x131x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x79x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x79x139x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x139x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x79x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x147x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x147x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x155x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x155x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x163x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x163x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x79x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x79x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x79x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x79x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[4];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2042x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2042x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x2048x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Stride1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x2048x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:172
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];TransposedConvBinWinoRxS<3-2>:161
2x512x7x7x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:162
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:176
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x7x7x1x1x1x1x2048x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:64
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:255
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,52;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+8
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:245
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:247
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:193
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:214
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];TransposedConvBinWinoRxS<3-2>:218
2x512x7x7x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;TransposedConvBinWinoRxS<3-2>:255
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;TransposedConvBinWinoRxS<3-2>:255
2x512x7x7x1x1x1x1x2048x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:249
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:242
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:244
2x512x7x7x1x1x1x1x2048x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:244
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:233
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x1x1x1x2048x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:210
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:216
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x1x1x1x2048x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x2048x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x2048x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,4,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[4];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Default, 32, 32, 1, 2, 4, 2, 1, 1>+32
2x512x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x2048x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+2
2x512x7x7x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x7x7x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x256x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+32
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,5,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x512x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,5,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x512x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x7x7x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x500x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Default, 32, 32, 1, 2, 4, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,4,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:235
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:235
2x512x7x7x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:211
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:192
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];TransposedConvBinWinoRxS<3-2>:209
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:193
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:107
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];TransposedConvBinWinoRxS<3-2>:118
2x512x7x7x1x3x3x1x512x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:167
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:160
2x512x7x7x1x3x3x1x512x15x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:203
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:164
2x512x7x7x1x3x3x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:89
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:88
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];TransposedConvBinWinoRxS<3-2>:103
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];TransposedConvBinWinoRxS<3-2>:94
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,92[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;TransposedConvBinWinoRxS<3-2>:248
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:241
2x512x7x7x1x3x3x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:231
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:237
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:232
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:231
2x512x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x312x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:239
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:236
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:238
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:235
2x512x7x7x1x3x3x1x512x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:158
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];TransposedConvBinWinoRxS<3-2>:144
2x512x7x7x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:155
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:145
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];TransposedConvBinWinoRxS<3-2>:154
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:147
2x512x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];TransposedConvBinWinoRxS<3-2>:163
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:161
2x512x7x7x1x3x3x1x512x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:222
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:160
2x512x7x7x1x3x3x1x512x35x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:231
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:230
2x512x7x7x1x3x3x1x512x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:246
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:230
2x512x7x7x1x3x3x1x512x408x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x512x7x7x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:248
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];TransposedConvBinWinoRxS<3-2>:248
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:248
2x512x7x7x1x3x3x1x512x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];TransposedConvBinWinoRxS<3-2>:246
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];TransposedConvBinWinoRxS<3-2>:250
2x512x7x7x1x3x3x1x512x51x1x1x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x7x7x1x3x3x1x512x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[2];TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];TransposedConvBinWinoRxS<3-2>:194
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:192
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:167
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:144
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];TransposedConvBinWinoRxS<3-2>:172
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];TransposedConvBinWinoRxS<3-2>:144
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[2];TransposedConvBinWinoRxS<3-2>:97
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];TransposedConvBinWinoRxS<3-2>:114
2x512x7x7x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:74
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:49
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,4,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[4];TransposedConvBinWinoRxS<3-2>:52
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,86;TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];TransposedConvBinWinoRxS<3-2>:70
2x512x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];TransposedConvBinWinoRxS<2-3>:256;TransposedConvBinWinoRxS<3-2>:256
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x7x7x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x7x7x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x7x7x1x3x3x1x512x96x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x7x7x1x7x7x1x4096x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x7x7x1x4096x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x7x7x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x7x7x1x7x7x1x4096x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,4,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[4];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x7x7x1x7x7x1x4096x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x7x7x1x7x7x1x4096x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x80x104x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x108x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x108x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x108x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x108x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x108x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x80x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x108x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x108x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x80x108x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x80x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x80x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x80x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x80x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x120x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x80x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x80x120x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x80x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x80x124x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x124x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x80x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x124x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x80x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x132x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x80x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x140x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x80x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x144x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x80x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x80x144x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x148x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x80x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x80x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x80x156x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x80x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x80x164x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x80x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x80x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x80x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x80x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x80x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x80x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x80x48x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x80x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x80x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x80x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x80x80x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x80x80x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x80x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x80x80x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x80x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x80x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x80x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x80x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x80x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x83x103x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x103x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x83x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x83x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x83x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x83x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x83x123x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x83x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x83x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x83x131x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x83x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x83x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x83x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x147x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x155x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x155x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x83x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x163x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x83x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x83x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x83x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x104x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x104x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x104x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x104x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x104x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x84x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x84x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x104x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x104x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x84x104x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x84x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x84x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x84x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x112x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x112x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x112x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x112x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x84x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x112x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x112x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x84x116x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x84x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x116x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x84x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x84x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x84x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x84x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x124x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x84x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x84x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x84x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x132x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x84x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x84x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x84x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x84x148x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x84x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x84x156x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x84x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x84x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x84x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x164x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x84x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x84x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x84x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x84x168x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x84x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x84x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x84x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x84x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x84x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x84x84x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x84x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x84x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x84x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x84x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x84x84x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x84x84x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x84x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x84x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x84x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x84x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x87x107x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x87x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x87x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x87x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x87x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x87x123x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x87x123x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x87x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x87x131x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x87x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x139x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x139x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x147x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x147x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x155x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x87x155x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x87x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x163x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x87x163x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x87x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x87x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x87x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x87x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x100x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x88x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x100x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x100x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x100x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x108x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x88x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x88x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x88x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x120x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x88x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x88x120x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x120x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x88x120x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x88x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x88x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x124x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x88x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x132x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x88x132x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x132x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x88x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x88x140x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x88x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x88x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x88x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x148x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x88x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x88x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x88x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x88x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x88x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x88x156x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x88x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x88x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x88x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x88x164x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x88x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x88x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x88x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x88x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x88x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x88x80x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x88x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x88x80x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x88x80x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x88x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x88x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x88x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x88x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x88x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x88x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x88x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x896x1128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x896x1160x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x8x40x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x40x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x40x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x40x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x512x8x40x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x40x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x8x40x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x40x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x40x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x512x8x40x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x8x40x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x8x40x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x8x40x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x40x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x40x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x8x40x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x8x4x1x3x3x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x4x1x3x3x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x6x1x3x3x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x6x1x3x3x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x6x1x3x3x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,52;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x8x8x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x512x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x1x3x1x256x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,4,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[2];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x3x1x256x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x1x3x1x256x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x1x3x1x256x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x1x3x1x256x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x1x3x1x448x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x1x3x1x448x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x3x1x1x256x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[4];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[4];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,4,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[4];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x1x1x256x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x3x1x1x256x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x512x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x1x1x256x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,239[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x1x1x256x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x8x8x1x3x1x1x448x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[3];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x3x1x1x448x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,4,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x512x8x8x1x3x1x1x448x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,46;ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x1x1x448x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x1x1x448x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x3x1x1x448x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x1x1x448x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,3,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x8x1x3x1x1x448x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,58;ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x1x1x448x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x1x1x448x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x1x1x448x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x1x1x448x512x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x1x1x448x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x1x1x448x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x1x1x448x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x1x1x448x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x1x1x448x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x1x1x448x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x1x1x448x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x8x1x3x1x1x448x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x8x8x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,4,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,4,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x8x8x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,4,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[4];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x256x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x8x8x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x8x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x8x1x3x3x1x448x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x8x8x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x8x8x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x8x8x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x8x8x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x512x8x8x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x204x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x208x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x8x8x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x8x8x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,4,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[4];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x512x8x8x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x312x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x400x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x8x8x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x8x8x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x512x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x8x8x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,3,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,153[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,4,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x8x8x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x50x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x8x8x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x8x8x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x8x8x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x8x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x8x8x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x8x8x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x8x8x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x8x8x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x512x8x8x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x512xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x512x8x8x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x8x8x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x8x8x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x8x8x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x512x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[3];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x512x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x912x1144x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x912x1144x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x912x1144x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x91x107x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x91x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x91x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x91x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x91x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x91x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x91x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x123x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x123x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x91x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x91x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x139x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x139x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x91x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x147x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x91x147x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x155x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x91x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x91x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x91x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x928x1128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x512x928x1160x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,2,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x512x92x108x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x92x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x92x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x92x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x124x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x92x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x92x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x124x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x92x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x92x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x92x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x92x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x92x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x140x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x92x140x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x92x140x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x92x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x140x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x92x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x92x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x148x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x92x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x92x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x148x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x92x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x92x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x92x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x92x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x92x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x92x164x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x164x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x92x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x92x168x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x92x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x92x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x92x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x92x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x92x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x92x92x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x512x92x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x92x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x92x92x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x92x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x92x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x92x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x92x92x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x95x103x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x103x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x95x107x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x95x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x95x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x95x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x95x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x123x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x95x123x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x131x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x95x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x139x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x139x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x95x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x147x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x147x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x155x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x155x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x163x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x95x163x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x95x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x95x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x95x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x104x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x104x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x104x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x104x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x108x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x108x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x108x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x96x108x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x96x112x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x112x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x96x112x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x116x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x116x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x116x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x96x116x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x512x96x116x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x120x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x120x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x120x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x120x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x124x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x124x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x96x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x124x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x96x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x512x96x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x96x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x132x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x132x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x132x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x132x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x136x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x96x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x136x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x136x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x136x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x140x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x96x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x140x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x96x144x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x144x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x96x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x144x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x144x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x512x96x148x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x96x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x96x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x512x96x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x148x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x148x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x148x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x152x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x152x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x152x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x152x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x96x156x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x156x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x156x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x96x156x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x96x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x96x160x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x96x160x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x160x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x160x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x160x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x164x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x96x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x164x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x96x164x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x512x96x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x164x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x512x96x168x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x512x96x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x512x96x84x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x96x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x84x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x512x96x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x96x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x512x96x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x512x96x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x88x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x512x96x96x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x512x96x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x96x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x512x96x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x512x96x96x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x99x107x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x99x107x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x111x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x111x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x115x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x99x115x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x119x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x99x119x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x123x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x127x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x127x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x131x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x99x131x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x135x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x99x135x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x99x135x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x135x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x139x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x99x139x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x143x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x99x143x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x147x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x151x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x99x151x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x151x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x151x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x159x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x99x159x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x163x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x163x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x167x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x79x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x512x99x79x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x87x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x87x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x91x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x91x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x512x99x95x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x95x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x99x99x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x512x99x99x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x9x41x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x512x9x41x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,3,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x512x9x41x1x5x5x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,62[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,16[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x9x41x1x5x5x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x512x9x41x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x512x9x41x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 4, 4, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,141[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x512x9x41x1x5x5x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x9x9x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x512x9x9x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x9x9x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,3,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[3];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x512x9x9x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x9x9x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x512x9x9x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,303[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x512x9x9x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x512x9x9x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,4,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[4];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x512x9x9x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x513x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x513x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x513x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x51x1x1x1x1x1x1x10x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x51x28x28x1x5x5x1x51x1x2x2x0x1x1x0x1x1x0x0x51xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x520x14x14x1x3x3x1x520x4x1x1x0x1x1x0x1x1x0x0x520xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x520x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2032x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2032x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2064x2032x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x520x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x520x2064x2064x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x528x112x112x1x3x3x1x528x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:225;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x112x112x1x3x3x1x528x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x128x128x1x1x1x1x136x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x12x12x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x528x12x12x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x528x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x136x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x528x14x14x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x528x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x528x14x14x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x14x14x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x14x14x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x14x14x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x14x14x1x5x5x1x528x1x2x2x0x1x1x0x1x1x0x0x528xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x528x14x14x1x5x5x1x528x1x2x2x0x2x2x0x1x1x0x0x528xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x528x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x256x256x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x528x256x256x1x5x5x1x528x1x2x2x0x1x1x0x1x1x0x0x528xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x528x256x256x1x5x5x1x528x4x2x2x0x1x1x0x1x1x0x0x528xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x528x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x528x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x528x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x28x28x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x32x32x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x32x32x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x32x32x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x4x4x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x4x4x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x528x512x512x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x528x512x512x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x56x56x1x3x3x1x528x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x528x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x528x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x64x64x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x64x64x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x64x64x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x528x64x64x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x64x64x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x528x64x64x1x3x3x1x528x4x1x1x0x1x1x0x1x1x0x0x22xNCHWxFP16xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x528x7x7x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x1x1x1x2112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x1x1x1x88x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x528x7x7x1x3x3x1x528x1x1x1x0x1x1x0x1x1x0x0x22xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x52x128x128x1x3x3x1x52x1x1x1x0x2x2x0x1x1x0x0x52xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x52x14x14x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x14x14x1x1x1x1x312x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x14x14x1x3x3x1x52x1x1x1x0x1x1x0x1x1x0x0x52xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x52x14x14x1x3x3x1x52x4x1x1x0x1x1x0x1x1x0x0x52xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x52x1x1x1x1x1x1x1160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x1x1x1x1x1x1x1228x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x1x1x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x1x1x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x52x256x256x1x3x3x1x52x1x1x1x0x1x1x0x1x1x0x0x52xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x52x28x28x1x1x1x1x156x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x512x512x1x3x3x1x52x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x52x56x56x1x3x3x1x22x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x52x64x64x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x532x7x7x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x532x7x7x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x538x64x64x1x3x3x1x538x1x1x1x0x1x1x0x1x1x0x0x538xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x544x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x544x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x544x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x544x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x544x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x544x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x544x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x544x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x544x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x544x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x544x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x544x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x544x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x544x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x544x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x544x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x544x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x1025x1025x1x3x3x1x54x1x0x0x0x2x2x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x1025x1025x1x3x3x1x54x4x0x0x0x2x2x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x111x111x1x1x1x1x54x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x128x128x1x1x1x1x142x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x14x14x1x3x3x1x54x1x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x1x1x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x1x1x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x1x1x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x256x256x1x1x1x1x142x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x28x28x1x1x1x1x216x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x54x28x28x1x1x1x1x216x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x54x28x28x1x1x1x1x216x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x28x28x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x28x28x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x28x28x1x1x1x1x216x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x28x28x1x1x1x1x216x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x28x28x1x1x1x1x216x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
2x54x28x28x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x1x1x1x216x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x28x28x1x3x3x1x54x1x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x54x28x28x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x54x28x28x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x28x28x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,214[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x54x29x29x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x29x29x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x29x29x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x54x29x29x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x54x29x29x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x29x29x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x29x29x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x54x29x29x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x54x29x29x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,16,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,216[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,122[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x54x512x512x1x1x1x1x17x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x512x512x1x1x1x1x324x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x512x512x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x512x512x1x3x3x1x54x4x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x512x512x1x5x5x1x54x4x2x2x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x512x512x1x7x7x1x54x1x3x3x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x513x513x1x3x3x1x54x1x0x0x0x2x2x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x54x55x55x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x54x55x55x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x55x55x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x54x55x55x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x55x55x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x1x1x1x17x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x56x56x1x1x1x1x324x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x54x56x56x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x4x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x54x56x56x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x56x56x1x7x7x1x54x1x3x3x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x57x57x1x3x3x1x54x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x57x57x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x54x7x7x1x3x3x1x54x1x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x7x7x1x3x3x1x54x4x1x1x0x1x1x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x552x14x14x1x1x1x1x108x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x552x14x14x1x1x1x1x108x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x560x128x128x1x1x1x1x560x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x560x128x128x1x3x3x1x560x1x1x1x0x1x1x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x560x128x128x1x3x3x1x560x1x1x1x0x2x2x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x560x14x14x1x1x1x1x1360x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x560x64x64x1x1x1x1x1680x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x560x64x64x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x560x7x7x1x1x1x1x1680x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x560x7x7x1x1x1x1x3840x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x560x7x7x1x1x1x1x3840x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x560x7x7x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x560x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x5632x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x5632x64x64x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x56x1024x1024x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1024x1024x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x112x112x1x3x3x1x112x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x56x112x112x1x3x3x1x112x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x56x128x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x128x128x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x128x128x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x128x128x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x128x128x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x56x14x14x1x3x3x1x56x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x1248x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x1344x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x14x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[7];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[9];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x56x1x1x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x1x1x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x256x256x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x256x256x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x256x256x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x256x256x1x3x3x1x448x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x56x256x256x1x3x3x1x56x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x56x256x256x1x3x3x1x56x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x56x264x264x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x264x264x1x3x3x1x56x1x1x1x0x1x1x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x168x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x168x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x56x28x28x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x56x28x28x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x56x28x28x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x56x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x56x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x56x28x28x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x3x3x1x448x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x56x28x28x1x3x3x1x56x1x1x1x0x1x1x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x28x28x1x3x3x1x56x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x56x32x32x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x512x512x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x512x512x1x3x3x1x56x4x1x1x0x2x2x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x512x512x1x3x3x1x56x4x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x56x56x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x56x56x1x3x3x1x224x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x56x56x56x1x3x3x1x56x1x1x1x0x2x2x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x56x56x1x5x5x1x56x1x2x2x0x2x2x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x64x64x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x64x64x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x64x64x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x56x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x56x64x64x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x64x64x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x56x64x64x1x1x1x1x336x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x56x64x64x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x56x64x64x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x56x64x64x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x56x64x64x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x56x64x64x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x56x64x64x1x3x3x1x56x1x1x1x0x1x1x0x1x1x0x0x56xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x56x7x7x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x570x128x128x1x3x3x1x570x1x1x1x0x1x1x0x1x1x0x0x570xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x112x112x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x112x112x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x576x112x112x1x1x1x1x336x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x112x112x1x1x1x1x336x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x576x128x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x128x128x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x128x128x1x1x1x1x1296x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x128x128x1x1x1x1x1512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x128x128x1x1x1x1x1512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x128x128x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x128x128x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x128x128x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x576x128x128x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x128x128x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x128x128x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x128x128x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x128x128x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x12x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x576x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x12x8x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x12x8x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x576x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x12x8x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+2
2x576x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x12x8x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x576x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x12x8x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x12x8x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x12x8x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x12x8x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x12x8x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x576x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x1296x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x1512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x1512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x576x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x18xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x576x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,57[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,185[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x576x14x14x1x3x3x1x576x16x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x576x14x14x1x3x3x1x576x32x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x576x14x14x1x3x3x1x576x64x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x4x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x14x14x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x14x14x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x15x15x1x3x3x1x576x1x0x0x0x2x2x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x576x16x16x1x1x1x1x1152x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x16x16x1x1x1x1x1152x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x1152x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x1152x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x16x16x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x16x16x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x16x16x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x16x16x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x16x16x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x16x16x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x16x16x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x16x16x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+8
2x576x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x576x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x16x16x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x16x16x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x576x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x16x16x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x16x16x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x16x16x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x17x17x1x1x1x1x2304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x17x17x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x17x17x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x19x19x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x19x19x1x5x5x1x576x4x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x576x1x1x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x1x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x1x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x1x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x1x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x1x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x1728x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x1728x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x576x1x30x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x576x1x30x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x576x1x30x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x576x1x30x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x576x1x30x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x1x1x66x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,280[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x66x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x1x30x1x1x1x1x66x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x1x30x1x1x1x1x66x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x66x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x1x30x1x1x1x1x66x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x66x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x66x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x576x1x30x1x1x1x1x66x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x576x1x30x1x1x1x1x66x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x1x30x1x1x1x1x66x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x1x30x1x1x1x1x66x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x1x1x66x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x1x1x66x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x1x1x66x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x1x1x66x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x1x30x1x1x3x1x576x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x576x1x30x1x1x3x1x576x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+1
2x576x1x30x1x1x3x1x576x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,327[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x1x30x1x1x3x1x576x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x1x30x1x1x3x1x576x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x1x30x1x1x3x1x576x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x1x30x1x1x3x1x576x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x576x1x30x1x1x3x1x576x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x1x30x1x1x3x1x576x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x1x30x1x1x3x1x576x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x1x30x1x1x3x1x576x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x1x30x1x1x3x1x576x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x576x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x256x256x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x576x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x28x28x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x576x28x28x1x1x1x1x336x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x576x28x28x1x1x1x1x336x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x28x28x1x1x1x1x336x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x576x28x28x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x28x28x1x3x3x1x576x1x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x32x32x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x32x32x1x1x1x1x3456x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x32x32x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x32x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x32x32x1x5x5x1x576x1x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x48x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x48x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,187[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x576x48x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x1x1x1x2048x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x2048x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x2048x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x2048x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x512x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x512x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x512x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x512x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x512x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x512x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x576x48x32x1x1x1x1x672x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x672x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x672x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x672x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x576x48x32x1x1x1x1x672x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x48x32x1x1x1x1x672x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+2
2x576x48x32x1x1x1x1x672x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x48x32x1x1x1x1x672x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+8
2x576x48x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x1x1x1x672x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x1x1x1x672x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x576x48x32x1x1x1x1x672x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
2x576x48x32x1x3x3x1x576x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x3x3x1x576x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x3x3x1x576x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x576x48x32x1x3x3x1x576x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,279[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x48x32x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x48x32x1x3x3x1x576x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x3x3x1x576x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x48x32x1x3x3x1x576x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x48x32x1x3x3x1x576x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x576x48x32x1x3x3x1x576x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x576x48x32x1x3x3x1x576x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x576x48x32x1x3x3x1x576x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x576x48x32x1x3x3x1x576x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,299[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x48x32x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x576x48x32x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x576x48x32x1x3x3x1x576x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x3x3x1x576x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,271[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x576x48x32x1x3x3x1x576x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x576x48x32x1x3x3x1x576x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x576x48x32x1x3x3x1x576x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+2
2x576x48x32x1x3x3x1x576x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x48x32x1x3x3x1x576x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x48x32x1x3x3x1x576x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x48x32x1x3x3x1x576x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x48x32x1x3x3x1x576x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x576x4x4096x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x4x49x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x64x64x1x1x1x1x1296x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x64x64x1x1x1x1x1296x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x64x64x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x64x64x1x1x1x1x2304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x64x64x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x64x64x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x64x64x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x64x64x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x36xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x576x64x64x1x3x3x1x576x1x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x65x65x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x69x69x1x3x3x1x576x4x0x0x0x1x1x0x2x2x0x0x576xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x576x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x576x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x576x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x576x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x576x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x576x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x576x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x576x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+16
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x16x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x3x3x1x576x16x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x16x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 4>+-1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x3x3x1x576x32x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x3x3x1x576x32x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x32x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x3x3x1x576x64x1x1x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x3x3x1x576x64x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x3x3x1x576x64x1x1x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x5x5x1x576x16x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x576x7x7x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x16x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x5x5x1x576x32x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x576x7x7x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x32x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x5x5x1x576x4x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x576x7x7x1x5x5x1x576x64x2x2x0x1x1x0x1x1x0x0x576xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x576x7x7x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x576x7x7x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x576x7x7x1x5x5x1x576x64x2x2x0x2x2x0x1x1x0x0x576xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x57x14x14x1x5x5x1x57x1x2x2x0x1x1x0x1x1x0x0x57xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x57x14x14x1x7x7x1x57x4x3x3x0x1x1x0x1x1x0x0x57xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x57x28x28x1x7x7x1x57x4x3x3x0x1x1x0x1x1x0x0x57xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x584x32x32x1x9x9x1x584x1x4x4x0x1x1x0x1x1x0x0x584xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x584x64x64x1x9x9x1x584x1x4x4x0x1x1x0x1x1x0x0x584xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x584x7x7x1x9x9x1x584x1x4x4x0x1x1x0x1x1x0x0x584xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x58x112x112x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x112x112x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x113x113x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x113x113x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x223x223x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x224x224x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x224x224x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x225x225x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x225x225x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x24x24x1x3x3x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+8
2x58x24x24x1x3x3x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x58x256x256x1x3x3x1x58x1x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x26x26x1x3x3x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x58x26x26x1x3x3x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x27x27x1x3x3x1x58x1024x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x27x27x1x3x3x1x58x1024x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x27x27x1x3x3x1x58x512x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x27x27x1x3x3x1x58x512x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,4,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,1,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,231[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[9];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x58x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x58x28x28x1x1x1x1x58x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x28x28x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 4, 1, 1>+4
2x58x28x28x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x28x28x1x3x3x1x58x1024x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x1024x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x1024x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+32
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+32
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x16x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x58x28x28x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 2>+32
2x58x28x28x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+64
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+64
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x32x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+32
2x58x28x28x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x512x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x512x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x512x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+-1
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+-1
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x28x28x1x3x3x1x58x64x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+64
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 2>+64
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x28x28x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x29x29x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x29x29x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x58x29x29x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x58x29x29x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x58x512x512x1x3x3x1x58x4x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x55x55x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,151[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x58x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x58x56x56x1x1x1x1x348x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x1024x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x16x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x32x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x512x0x0x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x58x56x56x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x58x56x56x1x3x3x1x58x64x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x57x57x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x58x57x57x1x3x3x1x58x512x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+2
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+4
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x5x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 8, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x5x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x5x256x256x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x512x512x1x3x3x1x5x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x5x56x56x1x3x3x1x5x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x600x256x256x1x1x1x1x122x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x600x32x32x1x1x1x1x100x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x600x64x64x1x1x1x1x100x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x608x128x128x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x128x128x1x3x3x1x608x1x1x1x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x608x130x130x1x3x3x1x608x4x0x0x0x2x2x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x608x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x608x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x608x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x14x14x1x1x1x1x304x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x608x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x608x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x14x14x1x3x3x1x608x1x1x1x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x608x14x14x1x3x3x1x608x4x1x1x0x2x2x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x28x28x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x32x32x1x3x3x1x608x1x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x608x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x64x64x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x608x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x64x64x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x64x64x1x1x1x1x2432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x608x64x64x1x3x3x1x608x1x1x1x0x2x2x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x608x64x64x1x7x7x1x608x4x3x3x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x608x7x7x1x1x1x1x1216x1x0x0x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x608x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x608x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x608x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x608x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x608x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x608x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x608x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x1x1x1x608x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x608x7x7x1x7x7x1x608x4x3x3x0x1x1x0x1x1x0x0x608xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x60x111x111x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x111x111x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x111x111x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x111x111x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x112x112x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x112x112x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x112x112x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x113x113x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x113x113x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x113x113x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x128x128x1x1x1x1x30x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x60x128x128x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,106[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x13x13x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,36;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x13x13x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x13x13x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x13x13x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x60x13x13x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x13x13x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x13x13x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+16
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x60x13x13x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x14x14x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x60x14x14x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x60x14x14x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x14x14x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,106[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x14x14x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+1
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x60x14x14x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x14x14x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x14x14x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x14x14x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x14x14x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x14x14x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+2
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,2,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x60x14x14x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,106[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x15x15x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x15x15x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+4
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x15x15x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x15x15x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x15x15x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x15x15x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x60x15x15x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x15x15x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x15x15x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x60x15x15x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x15x15x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x15x15x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Default, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+8
2x60x15x15x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x60x15x15x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x15x15x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x15x15x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x15x15x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x1x1x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x60x1x1x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x1x1x1x1x1x1x360x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x60x256x256x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x256x256x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x256x256x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x256x256x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x256x256x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x256x256x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x256x256x1x5x5x1x60x1x2x2x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x261x261x1x7x7x1x60x1x0x0x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x60x27x27x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x27x27x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x27x27x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x60x28x28x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 2, 1, 2, 4, 2, 4, 1, 1, 2>+-1
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x60x28x28x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x60x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x60x28x28x1x1x1x1x30x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x60x28x28x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x28x28x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[2];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+16
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x60x28x28x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,164[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x28x28x1x3x3x1x60x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x28x28x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+16
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+8
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 2, 1, 2, 1, 1, 1, 4>+8
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x28x28x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,167[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x60x28x28x1x3x3x1x60x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x28x28x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x28x28x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+2
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x28x28x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x60x28x28x1x3x3x1x60x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+4
2x60x28x28x1x3x3x1x60x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x60x28x28x1x3x3x1x60x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x60x28x28x1x3x3x1x60x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x60x28x28x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x28x28x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x29x29x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x29x29x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x29x29x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x29x29x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x60x29x29x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x29x29x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x29x29x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x29x29x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x29x29x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x60x29x29x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x29x29x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x512x512x1x9x9x1x60x1x4x4x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x513x513x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x519x519x1x9x9x1x60x1x0x0x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x56x56x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x56x56x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9]
2x60x56x56x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x56x56x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x56x56x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x60x56x56x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x56x56x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x56x56x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x56x56x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x60x56x56x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x60x56x56x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x56x56x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x56x56x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x56x56x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x56x56x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x56x56x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x56x56x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x56x56x1x5x5x1x60x1x2x2x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x56x56x1x7x7x1x60x4x3x3x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x56x56x1x9x9x1x60x1x4x4x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x57x57x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4]
2x60x57x57x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x57x57x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x57x57x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,1,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x57x57x1x3x3x1x60x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x60x57x57x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x57x57x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x60x57x57x1x3x3x1x60x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x60x57x57x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x57x57x1x3x3x1x60x4x0x0x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x60x57x57x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x57x57x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x57x57x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x57x57x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x60x57x57x1x3x3x1x60x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x60x57x57x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x60x57x57x1x3x3x1x60x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x60x61x61x1x7x7x1x60x1x0x0x0x2x2x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x60x64x64x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x60x64x64x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x60xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x6144x14x14x1x3x3x1x6144x1x1x1x0x2x2x0x1x1x0x0x6144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x6144x1x1x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x6144x1x1x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,5,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x6144x32x32x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[3];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x6144x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x6144x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x6144x64x64x1x1x1x1x1536x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x6144x64x64x1x3x3x1x6144x1x1x1x0x1x1x0x1x1x0x0x6144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x6144x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,5,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x6144x7x7x1x3x3x1x6144x4x1x1x0x1x1x0x1x1x0x0x6144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x61x1x1x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x61x1x1x1x1x1x1x732x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x61x1x1x1x1x1x1x732x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x61x256x256x1x3x3x1x61x1x1x1x0x1x1x0x1x1x0x0x61xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x61x256x256x1x5x5x1x61x1x2x2x0x1x1x0x1x1x0x0x61xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x61x256x256x1x5x5x1x61x4x2x2x0x1x1x0x1x1x0x0x61xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x61x512x512x1x1x1x1x17x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x61x512x512x1x1x1x1x17x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x61x56x56x1x1x1x1x17x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x624x128x128x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x128x128x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x128x128x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x128x128x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x128x128x1x3x3x1x624x4x1x1x0x2x2x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,2,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x104x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x624x14x14x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x624x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x624x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x624x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x14x14x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x16x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x624x14x14x1x3x3x1x624x1x1x1x0x2x2x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x32x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x14x14x1x5x5x1x624x16x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x5x5x1x624x32x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x14x14x1x5x5x1x624x64x2x2x0x1x1x0x1x1x0x0x624xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x624x1x1x1x1x1x1x156x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x1x1x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x256x256x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x28x28x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x624x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x624x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x624x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x624x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x32x32x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x512x512x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x512x512x1x3x3x1x624x4x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x56x56x1x1x1x1x104x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x56x56x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x624x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x624x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x64x64x1x1x5x1x624x4x0x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x64x64x1x3x3x1x624x1x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x64x64x1x3x3x1x624x4x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x64x64x1x5x1x1x624x4x2x0x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x7x7x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x7x7x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x624x7x7x1x1x5x1x624x1x0x2x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x624x7x7x1x3x3x1x624x1x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x624x7x7x1x5x1x1x624x1x2x0x0x1x1x0x1x1x0x0x624xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x62x1x1x1x1x1x1x1488x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x62x256x256x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x62x56x56x1x3x3x1x62x4x1x1x0x1x1x0x1x1x0x0x62xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x636x128x128x1x1x1x1x117x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x636x14x14x1x3x3x1x636x4x1x1x0x1x1x0x1x1x0x0x636xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x636x64x64x1x1x1x1x117x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x637x1x1x1x1x1x1x27x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x640x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x640x128x128x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x128x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x1x1x1x640x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x1280x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x2560x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x640x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x128x128x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x14x14x1x1x1x1x1056x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[4];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,150;ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x640x14x14x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,256,16,32,32,2,1,2,2,2,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,16,1,16,1,16,5[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x640x14x14x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x640x14x14x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x640x14x14x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x640x14x14x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x640x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x1x1x1x640x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x3x3x1x2560x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x14x14x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x14x14x1x3x3x1x640x1x1x1x0x2x2x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x14x14x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x14x14x1x5x5x1x640x4x2x2x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x16x16x1x1x1x1x1280x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:231
2x640x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x16x16x1x1x1x1x1280x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:151
2x640x16x16x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x640x16x16x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[8];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x16x16x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:211
2x640x16x16x1x1x1x1x640x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:249
2x640x16x16x1x1x1x1x640x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:165
2x640x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1;TransposedConvBinWinoRxS<3-2>:186
2x640x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:186
2x640x16x16x1x1x1x1x640x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1;TransposedConvBinWinoRxS<2-3>:210;TransposedConvBinWinoRxS<3-2>:203
2x640x16x16x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x16x16x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x16x16x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x640x16x16x1x3x3x1x1280x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x640x16x16x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x16x16x1x3x3x1x640x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x16x16x1x3x3x1x640x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x16x16x1x3x3x1x640x280x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x16x16x1x3x3x1x640x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x16x16x1x3x3x1x640x30x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:227
2x640x16x16x1x3x3x1x640x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x16x16x1x3x3x1x640x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+2
2x640x16x16x1x3x3x1x640x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x16x16x1x3x3x1x640x6x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:173
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4;TransposedConvBinWinoRxS<3-2>:183
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:238
2x640x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1;TransposedConvBinWinoRxS<2-3>:229;TransposedConvBinWinoRxS<3-2>:211
2x640x18x18x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x19x19x1x1x1x1x3840x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x1x1x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x1x1x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x24x24x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x24x24x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x256x256x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x256x256x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x640x256x256x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x640x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x28x28x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x28x28x1x5x5x1x640x4x2x2x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x32x32x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x32x32x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x32x32x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x640x32x32x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x1920x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x640x32x32x1x1x1x1x2560x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x1x1x1x320x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x32x32x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x640x32x32x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
2x640x32x32x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x32x32x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x640x32x32x1x1x1x1x320x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x32x32x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x32x32x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x640x32x32x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x32x32x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x640x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x1280x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x32x32x1x3x3x1x1920x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x320x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x32x32x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x640x32x32x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x32x32x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x640x32x32x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x32x32x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x32x32x1x3x3x1x640x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:193
2x640x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,2,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,102[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x640x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x960x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x32x32x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x640x32x32x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,4,1,4,1,64,94;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x640x32x32x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x640x40x40x1x3x3x1x640x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x48x48x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x4x16x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x4x16x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x64x64x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x64x64x1x1x1x1x1920x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x1x1x1x2560x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x1x1x1x320x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x1x1x1x320x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x1x1x1x320x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x1x1x1x320x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x64x64x1x3x3x1x1280x1x1x1x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x640x64x64x1x3x3x1x320x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:155
2x640x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,217[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x64x64x1x3x3x1x320x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x320x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x64x64x1x3x3x1x640x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x64x64x1x3x3x1x640x1x1x1x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x64x64x1x3x3x1x640x1x1x1x0x2x2x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:209
2x640x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x640x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x64x64x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[5];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x640x64x64x1x3x3x1x960x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x640x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x640x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,316[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x640x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x640x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x640x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x640x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x640x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x7x7x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x7x7x1x3x3x1x2560x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x3x3x1x960x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x3x3x1x960x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x7x7x1x7x7x1x640x1x3x3x0x1x1x0x1x1x0x0x640xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x640x80x80x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x80x80x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x80x80x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x8x8x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x8x8x1x1x1x1x1280x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x8x8x1x3x3x1x1280x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x8x8x1x3x3x1x1280x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x8x8x1x3x3x1x1280x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x640x8x8x1x3x3x1x640x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x8x8x1x3x3x1x640x280x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x8x8x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x8x8x1x3x3x1x640x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x640x96x96x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x96x96x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x640x9x9x1x1x1x1x3840x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x648x14x14x1x3x3x1x648x4x1x1x0x1x1x0x1x1x0x0x648xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x648x64x64x1x3x3x1x648x1x1x1x0x1x1x0x1x1x0x0x648xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x1018x1018x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1018x1018x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1024x1024x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1024x1024x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1024x1024x1x1x1x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x1024x1024x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x64x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x1024x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x1024x1024x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x1024x1024x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1024x1024x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x1024x1024x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x1024x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1024x1024x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1024x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1024x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1026x1026x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x1027x1027x1x5x5x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x1029x1029x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x1030x1030x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1030x1030x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x104x104x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x104x104x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,223[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x108x108x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x108x108x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x108x108x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x108x108x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x109x109x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x109x109x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x109x109x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x109x109x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x109x109x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x109x109x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x10x10x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x110x110x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x110x110x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x110x110x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x111x111x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x111x111x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x12x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x208x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x111x111x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x312x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x400x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x48x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x50x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x111x111x1x7x7x1x3x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x624x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3]
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3]
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x3x3x1x128x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x112x112x1x3x3x1x160x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x112x112x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x112x112x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x112x112x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x112x112x1x4x4x1x192x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x112x112x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x112x112x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x5x5x1x64x1x2x2x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x112x112x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:234
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:238
2x64x112x112x1x7x7x1x3x15x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:226
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:247
2x64x112x112x1x7x7x1x3x35x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:256
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:256
2x64x112x112x1x7x7x1x3x408x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x112x112x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:246
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:256
2x64x112x112x1x7x7x1x3x51x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x112x112x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x112x112x1x7x7x1x3x96x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x112x112x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x113x113x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x113x113x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x113x113x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x113x113x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x113x113x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x113x113x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x113x113x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x113x113x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x113x113x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x113x113x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1144x912x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1144x912x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1144x912x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1144x912x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x1144x912x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x114x114x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x114x114x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x114x114x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x204x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x114x114x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x114x114x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x114x114x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x5x5x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x115x115x1x5x5x1x64x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x115x115x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x115x115x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x115x115x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x115x115x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x115x115x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x117x117x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x117x117x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x117x117x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x125x125x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1280x1280x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1280x1280x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1280x1280x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1280x1280x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x1280x1280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1280x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x1536x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x1536x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x1664x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x1664x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1280x1856x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x1856x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x2240x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x1280x2240x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x2368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x2368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x2432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x2432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1280x2496x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x2496x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1280x2560x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1280x2560x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1283x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1283x1539x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x1539x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1283x1667x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x1667x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1283x1859x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x1859x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1283x2243x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x2243x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1283x2371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x2371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1283x2435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x2435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1283x2499x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x2499x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1283x2563x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1283x2563x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x1x1x1x88x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x128x128x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x128x128x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x128x128x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x128x128x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x128x128x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x128x128x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x128x128x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x128x128x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x128x128x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x128x128x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x128x128x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x128x128x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x128x128x1x4x4x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x128x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x64x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x129x129x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x129x129x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x129x129x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x129x129x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x129x129x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x129x129x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x12x120x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x12x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x12x120x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x12x120x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x12x120x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x12x120x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x12x120x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x12x120x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x12x120x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x12x120x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x12x120x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x12x120x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x12x120x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x12x120x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x12x120x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x120x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x12x120x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x12x120x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x130x130x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x130x130x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x130x130x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1344x1664x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1344x1664x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1344x2496x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1344x2496x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1347x1667x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1347x1667x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1347x2499x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1347x2499x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x13x13x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x13x13x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,6,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x13x13x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x13x13x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x13x13x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x13x13x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x13x13x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x13x13x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1408x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1408x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1408x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1408x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1411x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1411x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1411x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1411x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1448x1448x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1448x1448x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1448x1448x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1448x1448x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1448x1448x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1449x1449x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1449x1449x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1449x1449x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1449x1449x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1449x1449x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x144x336x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x144x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x144x336x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x145x145x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x145x145x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x145x145x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x145x145x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x146x146x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x146x146x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x146x146x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x146x146x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x146x146x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x1472x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1472x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1472x1728x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1472x1728x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1475x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1475x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1475x1731x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1475x1731x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x147x147x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x147x147x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x147x147x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x147x147x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x147x147x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x147x147x1x3x3x1x32x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x147x147x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x147x147x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x147x147x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x147x147x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x147x147x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x147x147x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x147x147x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x147x147x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x147x147x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x147x147x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x147x147x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x147x147x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x147x147x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x147x147x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x147x147x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x147x147x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x147x147x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x147x147x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x100x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x112x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x114x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x120x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x19x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x19x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x19x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x200x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x200x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x200x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x24x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x149x149x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x149x149x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x149x149x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x149x149x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x149x149x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x56x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x58x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x58x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x58x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x59x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x59x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x59x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x149x149x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[10];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[5];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,57[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[7];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[9];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x14x14x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x3x3x1x24x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+8
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x24x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[4];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x24x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x64x14x14x1x3x3x1x24x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x3x3x1x24x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x64x14x14x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>+1
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x14x14x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x24x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,287[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x24x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x5x5x1x24x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x24x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x5x5x1x24x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x64x14x14x1x5x5x1x24x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,126[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x5x5x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x24x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x64x14x14x1x5x5x1x24x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x5x5x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x5x5x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x64x14x14x1x5x5x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x5x5x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x14x14x1x5x5x1x24x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x24x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x14x14x1x5x5x1x24x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x24x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x14x14x1x5x5x1x24x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x5x5x1x24x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x5x5x1x24x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x24x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x64x14x14x1x5x5x1x24x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x5x5x1x24x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
2x64x14x14x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x64x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x64x14x14x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x64x14x14x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+32
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+16
2x64x14x14x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,16,64,16,4,1,1,2,1,1,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,259;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x64x14x14x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x14x14x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x14x14x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x64x14x14x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x64x14x14x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x64x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x14x14x1x5x5x1x64x1x2x2x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:255
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:256
2x64x150x150x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x150x150x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x200x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:256
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:244
2x64x150x150x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x150x150x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x64x150x150x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:246
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:247
2x64x150x150x1x7x7x1x3x3x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x150x150x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x150x150x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x59x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233
2x64x150x150x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140
2x64x1536x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1536x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1536x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1536x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x1536x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x64x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85
2x64x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2731x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1536x2731x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2731x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x1536x2731x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1536x2731x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2732x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2732x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2732x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1536x2732x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1536x2732x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x1539x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1539x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1539x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1539x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x153x153x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x19x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x153x153x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x153x153x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x153x153x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x153x153x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x153x153x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6]
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x157x696x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x157x696x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8]
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x159x698x1x5x5x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x159x698x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x159x698x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x159x698x1x5x5x1x1x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1600x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1600x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1600x1728x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1600x1728x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1600x2176x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1600x2176x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1600x2432x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1600x2432x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1603x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1603x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1603x1731x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1603x1731x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1603x2179x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1603x2179x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1603x2435x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1603x2435x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x160x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:189;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x160x1x1x3x1x128x4x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x160x160x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x160x160x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x160x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x160x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x64x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x64x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x216x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x216x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x216x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x160x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x160x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x240x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x240x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x240x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x160x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x248x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x248x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x248x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x160x288x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x288x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x160x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 1, 1>+1
2x64x160x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x160x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x160x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x160x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x160x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x160x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x161x700x1x5x5x1x1x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x161x700x1x5x5x1x1x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x161x700x1x5x5x1x1x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,151;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x161x700x1x5x5x1x1x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x1664x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x1664x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1667x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1667x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x208x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x208x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x208x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x168x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x224x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x224x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x168x232x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x232x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x232x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x168x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x232x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x168x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x168x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x168x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x168x336x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x168x336x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x168x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x168x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x16x16x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x16x16x1x3x3x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x16x16x1x3x3x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x16x16x1x3x3x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x16x16x1x3x3x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x16x16x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x16x16x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x64x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:182;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x176x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x240x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x240x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x240x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x176x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x264x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x264x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x264x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x176x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x176x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x176x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x176x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x176x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x176x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x1792x1600x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1792x1600x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1792x1792x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1792x1792x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1792x1792x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1792x1792x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1792x1792x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1795x1603x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1795x1603x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1824x2288x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1824x2288x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1824x2288x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1824x2288x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1824x2288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x184x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x184x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x184x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x248x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x248x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x248x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x184x280x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x280x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x184x280x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x280x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x184x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x184x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x296x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x296x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x296x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:91;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x184x328x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x184x328x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x328x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x184x336x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x184x336x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x184x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x184x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x1856x1600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1856x1600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x1859x1603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x1859x1603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x18x18x1x3x3x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x18x18x1x3x3x1x24x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x18x18x1x3x3x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x18x18x1x3x3x1x24x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x18x18x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x64x18x18x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1920x1920x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x1920x1920x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x1920x1920x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x1920x1920x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1920x1920x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x192x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x192x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x192x192x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x192x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x192x1x4x4x1x192x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x208x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x208x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x208x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x232x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x232x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x232x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x192x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x288x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x288x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x288x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x192x296x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x296x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x296x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x312x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x312x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x312x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x192x320x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x320x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x192x320x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x192x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x192x336x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x336x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x192x336x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x192x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x192x336x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x19x19x1x1x1x1x1x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x2048x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x4096x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x2x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x2x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x1x1x1x3x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x19x19x1x1x1x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[9];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:224
2x64x19x19x1x3x3x1x13x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:3
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:196
2x64x19x19x1x3x3x1x13x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];TransposedConvBinWinoRxS<2-3>:26;TransposedConvBinWinoRxS<3-2>:3
2x64x19x19x1x3x3x1x13x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x19x19x1x3x3x1x13x2048x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:256
2x64x19x19x1x3x3x1x13x2048x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:2
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;TransposedConvBinWinoRxS<3-2>:202
2x64x19x19x1x3x3x1x13x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];TransposedConvBinWinoRxS<2-3>:10;TransposedConvBinWinoRxS<3-2>:3
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x19x19x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x19x19x1x3x3x1x13x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x13x4096x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];TransposedConvBinWinoRxS<3-2>:251
2x64x19x19x1x3x3x1x13x4096x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:2
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;TransposedConvBinWinoRxS<3-2>:196
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];TransposedConvBinWinoRxS<2-3>:22;TransposedConvBinWinoRxS<3-2>:3
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;TransposedConvBinWinoRxS<3-2>:205
2x64x19x19x1x3x3x1x13x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:3
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;TransposedConvBinWinoRxS<3-2>:98
2x64x19x19x1x3x3x1x13x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];TransposedConvBinWinoRxS<2-3>:10;TransposedConvBinWinoRxS<3-2>:5
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:249
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:4
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:209
2x64x19x19x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:26;TransposedConvBinWinoRxS<3-2>:14
2x64x19x19x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x19x19x1x3x3x1x64x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x2048x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:251
2x64x19x19x1x3x3x1x64x2048x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:62
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:213
2x64x19x19x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:20
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x19x19x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x19x19x1x3x3x1x64x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x4096x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:252
2x64x19x19x1x3x3x1x64x4096x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];TransposedConvBinWinoRxS<2-3>:20;TransposedConvBinWinoRxS<3-2>:4
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:240
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:26;TransposedConvBinWinoRxS<3-2>:5
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:239
2x64x19x19x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:4
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:199
2x64x19x19x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:115;TransposedConvBinWinoRxS<3-2>:14
2x64x1x1x1x1x1x1x128x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x64x1x1x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x1x1x1x1x1x1x128x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x1x1x1x1x1x1x128x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x1x1x1x1x1x1x128x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x1x1x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x1x1x1x1x1x1x128x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x64x1x1x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x64x1x1x1x1x1x1x128x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x1x1x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x128x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x1x1x1x1x1x1x128x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x166x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x64x1x1x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x1x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x1x1x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x64x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x1x1x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x1x1x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x216x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x200x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x224x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x232x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x232x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x240x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x240x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x248x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x248x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x248x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x264x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x264x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x264x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x272x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x272x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x272x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x272x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x272x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x280x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x280x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x288x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x288x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x288x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x296x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x200x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x296x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x200x304x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x304x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x304x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x312x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x312x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x200x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x312x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x320x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x320x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x200x328x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x200x328x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x200x328x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x328x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x200x336x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x200x336x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2040x2040x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2040x2040x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2040x2040x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2040x2040x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x2040x2040x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2047x2047x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2047x2047x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2047x2047x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2047x2047x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x2047x2047x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2048x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2048x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x2048x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x64x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85
2x64x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2048x2048x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4095x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x4095x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4095x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x2048x4095x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4096x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2048x4096x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4096x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x64x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4096x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x2048x4096x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2048x4096x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2048x4096x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4097x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>
2x64x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4097x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4097x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2048x4097x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x2048x4097x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2049x2049x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2049x2049x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2049x2049x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2049x2049x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x2049x2049x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2051x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2051x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2051x4099x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x2051x4099x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x207x207x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x207x207x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x207x207x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x207x207x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,123[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x207x207x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x208x160x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x208x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x208x160x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x208x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x208x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x208x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x208x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x208x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x208x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x208x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x208x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x208x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x208x208x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x208x208x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x208x208x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x208x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x208x208x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x208x208x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x208x208x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x208x208x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x208x208x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6]
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x208x208x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x208x208x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x208x208x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x208x208x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x209x209x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x209x209x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x209x209x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x209x209x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x209x209x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x209x209x1x3x3x1x32x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x20x20x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x20x30x1x3x3x1x128x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x20x30x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x2112x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2112x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2115x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2115x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x212x212x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x212x212x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x212x212x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x212x212x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x216x160x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x216x160x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x216x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x216x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x216x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x216x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x216x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x216x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x216x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x216x216x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x216x216x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x216x216x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x216x216x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x216x216x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x216x216x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x216x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x216x216x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x216x216x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x216x216x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x216x216x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2176x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2176x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2176x1600x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2176x1600x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2179x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2179x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2179x1603x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2179x1603x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x217x217x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x217x217x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x217x217x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x217x217x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x217x217x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x217x217x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x217x217x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x217x217x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x217x217x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x217x217x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x217x217x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x217x217x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x218x218x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x218x218x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x218x218x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x218x218x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x220x220x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x220x220x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x220x220x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x220x220x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:191;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,163;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x222x222x1x3x3x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x222x222x1x3x3x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x222x222x1x3x3x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x223x223x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x223x223x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x223x223x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x223x223x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x223x223x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x223x223x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x223x223x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2240x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2240x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2243x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2243x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x224x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x11x11x1x3x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x11x11x1x3x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x11x11x1x3x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x224x224x1x11x11x1x3x1x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x224x224x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x224x224x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x224x224x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x224x224x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x1x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x224x224x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x3x3x1x3x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x3x3x1x3x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[7];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10]
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9]
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x224x224x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x224x224x1x7x7x1x3x12x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:82;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x7x7x1x3x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x224x224x1x7x7x1x3x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x512x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x224x224x1x7x7x1x3x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x6x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x225x225x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x225x225x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x225x225x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x225x225x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x225x225x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x225x225x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x64x225x225x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x225x225x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x225x225x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x225x225x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x225x225x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x225x225x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x225x225x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x225x225x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x225x225x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x13x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x225x225x1x3x3x1x13x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x13x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x225x225x1x3x3x1x16x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x225x225x1x3x3x1x16x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x225x225x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x225x225x1x3x3x1x16x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x16x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x225x225x1x3x3x1x16x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x16x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x16x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x225x225x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x225x225x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x225x225x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x225x225x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x225x225x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x225x225x1x3x3x1x5x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x225x225x1x3x3x1x5x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x225x225x1x3x3x1x5x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x225x225x1x3x3x1x5x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x5x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x10x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x11x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x12x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x13x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x14x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x15x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x64x16x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x17x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x18x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x19x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x225x225x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x64x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x225x225x1x3x3x1x64x1x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x20x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x21x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x22x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x23x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x24x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x25x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x26x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x27x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x28x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x29x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x2x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x30x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x31x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x64x32x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x33x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x34x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x35x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x36x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x225x225x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x37x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x3x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x4x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x5x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x225x225x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x6x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x7x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x225x225x1x3x3x1x64x8x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x225x225x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x225x225x1x3x3x1x64x9x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x226x226x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x226x226x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x226x226x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x226x226x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x226x226x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x226x226x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x64x226x226x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x227x227x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x227x227x1x3x3x1x3x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x3x3x1x3x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x227x227x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x227x227x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x227x227x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x227x227x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x227x227x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x227x227x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x48x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x227x227x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x227x227x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x227x227x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x227x227x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x227x227x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x227x227x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x227x227x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x227x227x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2288x1824x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2288x1824x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x2288x1824x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2288x1824x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x2288x1824x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x228x228x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x228x228x1x3x3x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x228x228x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x228x228x1x3x3x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x229x229x1x3x3x1x3x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x229x229x1x3x3x1x3x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x2304x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2304x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2304x2304x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x2304x2304x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2304x2304x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x2304x2304x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x2304x2304x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x2307x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2307x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x230x230x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x230x230x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x230x230x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x230x230x1x3x3x1x3x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x232x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x232x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x232x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x232x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x232x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x232x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x232x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x232x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x232x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x232x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x232x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x232x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x232x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x232x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x232x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2368x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2368x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2368x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2368x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2371x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2371x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2371x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2371x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x240x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x240x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x240x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x240x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x240x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x240x176x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x240x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x240x176x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x240x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x240x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x240x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x240x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x160x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x248x160x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x160x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x184x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x248x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x248x184x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x248x192x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x248x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x248x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2496x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2496x1344x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2496x1472x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2496x1472x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2499x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2499x1347x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2499x1475x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2499x1475x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x24x16x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x24x16x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x24x16x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x24x16x1x1x1x1x35x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x24x24x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x24x24x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x253x253x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x254x254x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x2560x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2560x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2560x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2560x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2563x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2563x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2563x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2563x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x256x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x256x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x184x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x184x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x160x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x256x256x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[8]
2x64x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2]
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[9]
2x64x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x256x256x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7]
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x128x4x2x2x0x1x1x0x2x2x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x256x256x1x3x3x1x35x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x256x256x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x256x256x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x256x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9]
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x256x256x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x256x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x4x4x1x64x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x256x256x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x256x256x1x7x7x1x128x1x3x3x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x256x256x1x7x7x1x64x1x3x3x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x256x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x256x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x256x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x2624x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2624x1280x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2624x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2624x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2627x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x2627x1283x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x2627x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x2627x1411x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x264x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x264x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x264x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x176x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x264x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x264x176x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x264x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x264x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x264x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x264x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,55[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x264x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x264x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x264x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x26x26x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x272x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x272x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x272x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x176x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x272x176x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x272x176x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x272x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x272x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x272x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x272x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x272x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x272x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x27x27x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x27x27x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x27x27x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x27x27x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x27x27x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x27x27x1x5x5x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x64x27x27x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x64x27x27x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x5x5x1x192x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x4096x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x27x27x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x27x27x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x27x27x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x27x27x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x280x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x280x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x280x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x280x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x280x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x280x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:83;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x280x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x280x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x288x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x288x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x288x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x288x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x288x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x288x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x288x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x64x288x184x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x288x184x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x184x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x192x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x288x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x288x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x288x192x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x288x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x28x28x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,87[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x64x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,1,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,128[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x28x28x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x28x28x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x5x1x64x1x0x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x28x28x1x2x2x1x100x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,225[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x3x3x1x160x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x3x1x168x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 8>+-1
2x64x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x28x28x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x64x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x64x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x64x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x28x28x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x64x28x28x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x28x28x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x5x1x64x1x1x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x3x7x1x64x1x1x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x28x28x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x28x28x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x28x28x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x28x28x1x5x5x1x64x4x2x2x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x28x28x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12
2x64x296x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x296x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x296x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x296x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x296x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x296x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x296x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x296x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x296x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:69;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x296x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x296x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x296x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x296x296x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x29x29x1x3x3x1x192x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x29x29x1x3x3x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x29x29x1x3x3x1x192x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x29x29x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x2x2x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,1,0,4,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,37[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x64x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x64x300x300x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x300x300x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x300x300x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x300x300x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x300x300x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x300x300x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x300x300x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x300x300x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x304x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x304x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x304x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x304x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x304x192x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x304x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x304x192x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x304x192x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x304x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x304x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x304x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x304x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x30x30x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x312x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x312x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x312x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x312x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x312x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x312x168x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x312x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x312x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x312x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x312x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x312x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x312x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x312x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x312x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x312x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x312x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x312x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x312x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x312x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x319x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x319x383x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x383x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x319x415x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x415x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x319x463x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x463x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x319x559x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x559x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x319x591x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x591x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x319x607x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x607x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x319x623x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x623x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x319x639x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x319x639x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x31x31x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x31x31x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[4];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x320x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x320x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x320x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x320x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x320x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x320x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x320x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:183;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x320x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x320x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x320x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x320x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x320x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x320x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x320x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x320x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x320x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x320x200x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x320x320x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x320x320x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x320x320x1x3x1x1x64x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x320x320x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x320x320x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x320x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x320x384x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x384x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x416x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x416x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x464x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x464x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x320x560x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x560x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x320x592x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x592x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x320x608x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x608x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x320x624x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x624x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x320x640x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x320x640x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x323x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x323x387x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x387x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x323x419x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x419x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x323x467x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x467x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x323x563x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x563x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x323x595x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x595x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x323x611x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x323x611x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x323x627x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x323x627x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x323x643x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x323x643x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x328x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x328x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x328x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x328x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x328x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x328x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x328x160x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x328x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x328x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x328x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x328x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x328x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x328x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x328x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x328x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x328x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x328x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x328x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x32x32x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x32x32x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x32x32x1x3x3x1x128x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x32x32x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x32x32x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x32x32x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x32x32x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x32x32x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x32x32x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x32x32x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x32x32x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x32x32x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x32x32x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x32x32x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x32x32x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x32x32x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,44[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x64x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x335x415x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x335x415x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x335x623x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x335x623x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x336x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x336x160x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x168x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x336x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x336x168x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x336x168x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x336x176x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x184x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x184x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x336x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x336x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:81;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x336x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x336x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x336x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x336x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x336x416x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x336x416x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x336x624x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x336x624x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x339x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x339x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x339x419x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x339x419x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x339x627x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x339x627x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x33x33x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x33x33x1x3x3x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x33x33x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x33x33x1x4x4x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x33x33x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x33x33x1x4x4x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x33x33x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x33x33x1x4x4x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x34x34x1x4x4x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x34x34x1x4x4x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x34x34x1x4x4x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x351x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x351x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x351x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x351x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x352x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x352x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x352x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x352x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x355x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x355x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x355x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x355x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,5,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x35x35x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,16,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,2,1,4,1,64,127[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x35x35x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x35x35x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x288x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[8];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x64x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x64x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[5];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x288x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x64x35x35x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x3x3x1x48x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x35x35x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x35x35x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x35x35x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,111[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x35x35x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,319[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x64x35x35x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x35x35x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x35x35x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x35x35x1x5x5x1x48x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x64x35x35x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,307[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,159[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x64x35x35x1x5x5x1x48x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x64x35x35x1x5x5x1x48x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x84x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x35x35x1x5x5x1x48x86x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+2
2x64x35x35x1x5x5x1x48x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x367x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x367x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x367x431x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x367x431x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x368x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x368x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x368x432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x368x432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x371x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x371x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x371x435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x371x435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x37x37x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x37x37x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x37x37x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x37x37x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x37x37x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x383x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x383x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x383x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x383x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x384x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x384x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x384x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x384x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x387x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x387x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x387x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x387x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x38x19x1x1x3x1x64x10x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x10x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x11x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x11x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x12x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x12x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x13x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x13x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x14x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x14x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x15x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x15x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x17x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x17x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x38x19x1x1x3x1x64x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x19x1x1x3x1x64x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x19x1x1x3x1x64x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x2x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x2x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x19x1x1x3x1x64x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x3x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x38x19x1x1x3x1x64x3x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x1x3x1x64x4x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x4x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x1x3x1x64x5x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x5x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x6x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x6x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x7x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x7x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x1x3x1x64x8x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x8x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x1x3x1x64x9x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x1x3x1x64x9x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x10x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x10x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x10x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x11x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x11x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x11x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x12x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x64x38x19x1x5x1x1x64x12x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x12x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x13x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x13x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x13x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x14x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x14x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x14x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x15x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x15x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x15x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x16x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x16x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x16x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x17x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x17x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x17x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x18x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x18x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x18x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x19x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x19x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x19x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x38x19x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x1x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x19x1x5x1x1x64x20x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x20x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x20x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x21x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x21x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x21x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x22x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x22x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x22x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x23x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x23x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x23x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x24x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x24x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x24x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x25x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x25x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x25x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x26x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x26x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x26x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x27x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x27x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x27x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x28x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x28x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x28x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x29x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x19x1x5x1x1x64x29x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x29x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x2x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x38x19x1x5x1x1x64x2x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x2x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x19x1x5x1x1x64x30x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x30x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x19x1x5x1x1x64x30x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x31x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x19x1x5x1x1x64x31x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x31x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x32x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x32x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x32x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x33x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x33x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x33x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x34x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x34x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x34x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x35x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x35x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x38x19x1x5x1x1x64x35x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x38x19x1x5x1x1x64x36x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x36x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x36x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x37x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x37x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x19x1x5x1x1x64x37x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x19x1x5x1x1x64x3x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x64x38x19x1x5x1x1x64x3x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x3x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x5x1x1x64x4x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x38x19x1x5x1x1x64x4x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x4x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x5x1x1x64x5x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x38x19x1x5x1x1x64x5x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x5x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x6x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x64x38x19x1x5x1x1x64x6x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x6x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x5x1x1x64x7x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x7x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x7x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x19x1x5x1x1x64x8x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x8x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x8x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x19x1x5x1x1x64x9x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x19x1x5x1x1x64x9x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x19x1x5x1x1x64x9x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x10x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x11x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x12x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x13x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x14x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x15x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x17x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x38x38x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x38x1x1x3x1x64x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x38x38x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x1x3x1x64x2x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x1x3x1x64x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x3x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x1x3x1x64x4x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x5x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x6x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x7x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x8x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x1x3x1x64x9x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x38x38x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x38x38x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x38x38x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x64x38x38x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x38x38x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x38x38x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x38x38x1x3x3x1x64x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x38x38x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x38x38x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x38x38x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x38x38x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x38x38x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x38x38x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x64x38x38x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x38x38x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x38x38x1x3x3x1x64x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x38x38x1x3x3x1x64x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x399x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x399x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x399x431x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x399x431x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x399x543x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x399x543x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x399x607x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x399x607x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x39x39x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x39x39x1x3x3x1x48x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x39x39x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x39x39x1x3x3x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x400x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x400x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x400x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x400x432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x432x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x400x544x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x544x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x400x608x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x400x608x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x403x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x403x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x403x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x403x435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x435x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x403x547x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x547x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x403x611x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x403x611x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x40x60x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x40x60x1x3x3x1x192x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x40x60x1x3x3x1x192x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x40x60x1x3x3x1x192x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x192x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x40x60x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x40x60x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x40x60x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x40x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x40x60x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x40x60x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x40x60x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x40x60x1x3x3x1x64x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x40x60x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x40x60x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x40x60x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,123[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x413x413x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x415x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+2
2x64x415x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x415x415x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x415x415x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x416x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x416x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x417x417x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x417x417x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x417x417x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x417x417x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x417x417x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x417x417x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x417x417x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x417x417x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x419x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x419x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x432x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x432x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x432x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x432x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x432x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x432x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x435x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x435x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x435x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x435x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x435x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x435x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x445x445x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x445x445x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x445x445x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x447x399x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x447x399x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x448x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x400x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x400x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x448x448x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3]
2x64x448x448x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x448x448x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x448x448x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x448x448x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4]
2x64x448x448x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x448x448x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5]
2x64x448x448x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x448x448x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x449x449x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x449x449x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x449x449x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x449x449x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x449x449x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x449x449x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x449x449x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x449x449x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x449x449x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6]
2x64x449x449x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x449x449x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x449x449x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x403x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x403x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x451x451x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x451x451x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x100x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x204x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x208x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x312x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5]
2x64x451x451x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x451x451x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x400x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x451x451x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6]
2x64x451x451x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x451x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x50x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x451x451x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x624x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x451x451x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x452x452x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x452x452x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x452x452x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x452x452x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x452x452x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x452x452x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6]
2x64x452x452x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x452x452x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x452x452x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x452x452x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5]
2x64x452x452x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x452x452x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x452x452x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x452x452x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x453x453x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x453x453x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x463x399x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x463x399x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x464x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x464x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x464x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x464x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x464x400x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x464x400x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x467x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x467x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x467x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x467x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x467x403x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x467x403x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x480x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x480x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x480x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x480x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x480x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x480x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x483x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x483x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x483x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x483x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x483x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x483x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x48x32x1x1x1x1x35x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,225[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x48x32x1x1x1x1x35x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x64x48x32x1x1x1x1x35x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x48x32x1x1x1x1x35x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x48x32x1x1x1x1x35x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x35x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x48x32x1x1x1x1x35x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x64x48x32x1x1x1x1x35x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x64x48x32x1x1x1x1x35x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x48x32x1x1x1x1x35x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x48x32x1x1x1x1x35x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x48x32x1x1x1x1x35x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x48x32x1x1x1x1x35x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x35x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x48x32x1x1x1x1x35x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x48x32x1x1x1x1x35x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x48x32x1x1x1x1x35x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x48x32x1x1x1x1x67x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x67x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x67x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x48x32x1x1x1x1x67x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x67x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x67x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x48x32x1x1x1x1x67x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x48x32x1x1x1x1x67x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x64x496x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x496x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x496x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x496x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x499x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x499x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x499x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x499x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x4x16384x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x4x16384x1x1x1x1x129x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x4x16384x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x4x4x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x64x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x64x509x509x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x509x509x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x509x509x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x509x509x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x509x509x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x509x509x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x509x509x1x7x7x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x509x509x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x509x509x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x510x510x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x511x1023x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x511x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x511x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x1024x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x512x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x512x512x1x1x1x1x10x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x19x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x512x512x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x1x1x1x47x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x512x512x1x1x1x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x512x512x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x512x512x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x512x512x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x512x512x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x512x512x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x512x512x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x64x512x512x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x512x512x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x512x512x1x7x7x1x128x4x3x3x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x512x512x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x512x512x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x512x512x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x512x512x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x512x512x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x512x512x1x7x7x1x3x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x512x512x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x512x512x1x7x7x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x512x512x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x512x512x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x513x513x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x514x514x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x514x514x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x514x514x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x514x514x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x514x514x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x514x514x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x6x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x514x514x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x514x514x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x515x1027x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x515x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x515x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x515x515x1x5x5x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x517x517x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x51x51x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x51x51x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x51x51x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x527x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x527x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x528x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x528x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x528x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x528x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x528x368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x528x368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x52x52x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x52x52x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[9];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x52x52x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x52x52x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x531x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x531x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x531x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x531x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x531x371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x531x371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x53x53x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x53x53x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x53x53x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
2x64x53x53x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x53x53x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x53x53x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x11x11x1x3x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x53x53x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x53x53x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x53x53x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x53x53x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x53x53x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x53x53x1x3x3x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x53x53x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x53x53x1x3x3x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x53x53x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x543x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x543x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x543x399x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x543x399x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x544x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x544x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x544x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x544x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x544x400x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x544x400x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x547x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x547x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x547x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x547x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x547x403x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x547x403x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x54x54x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x54x54x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x54x54x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x54x54x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x54x54x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x54x54x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x54x54x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x54x54x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x64x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,125;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,125;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,215[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,81[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x64x54x54x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+16
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x64x54x54x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,61;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x54x54x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Default, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,61;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,80[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x54x54x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x54x54x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x54x54x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x559x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x559x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x16x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x11x11x1x3x1x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2048x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x256x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x2x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x32x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x32x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4096x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x4x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x512x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x64x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x11x11x1x3x8x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,173[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,8,1,1,8,1,32,1,4,1,1,1,8,1,32,99;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x55x55x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,69;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,169[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,93[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x55x55x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+8
2x64x55x55x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+4
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x55x55x1x3x3x1x16x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x55x55x1x3x3x1x16x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+2
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,72[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,131[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x55x55x1x3x3x1x3x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x55x55x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x55x55x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x64x55x55x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x64x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x55x55x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x55x55x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x55x55x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x55x55x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x55x55x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x55x55x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x55x55x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x55x55x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x55x55x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x560x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x560x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x560x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x560x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x560x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x560x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x563x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x563x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x563x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x563x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x563x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x563x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x56x56x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x16x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x56x56x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x56x56x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x56x56x1x11x11x1x3x1x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x2048x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x56x56x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x56x56x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x56x56x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x2x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x56x56x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x32x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x56x56x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x56x56x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x56x56x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x4x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x512x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x56x56x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x64x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x56x56x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,1,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x64x56x56x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x11x11x1x3x8x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 16, Filter1x1Pad0, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x1x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:19
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:80;TransposedConvBinWinoRxS<3-2>:58
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:17
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:23
2x64x56x56x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:23
2x64x56x56x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:32;TransposedConvBinWinoRxS<3-2>:40
2x64x56x56x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:22;TransposedConvBinWinoRxS<3-2>:241
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:249
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[2];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:79
2x64x56x56x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:241
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:19
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:19;TransposedConvBinWinoRxS<3-2>:25
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:32
2x64x56x56x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:249
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:40;TransposedConvBinWinoRxS<3-2>:28
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;TransposedConvBinWinoRxS<3-2>:251
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:19;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;TransposedConvBinWinoRxS<3-2>:240
2x64x56x56x1x1x1x1x256x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[9];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:27
2x64x56x56x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:22
2x64x56x56x1x1x1x1x256x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[1];TransposedConvBinWinoRxS<2-3>:20;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[6];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:17
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];TransposedConvBinWinoRxS<2-3>:24;TransposedConvBinWinoRxS<3-2>:18
2x64x56x56x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:45;TransposedConvBinWinoRxS<3-2>:32
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x2x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,136[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x45x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x56x56x1x1x1x1x45x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x56x56x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:60
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:250
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:247
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];TransposedConvBinWinoRxS<2-3>:20;TransposedConvBinWinoRxS<3-2>:41
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;TransposedConvBinWinoRxS<3-2>:172
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:44;TransposedConvBinWinoRxS<3-2>:8
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:213
2x64x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:181
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:185
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:60;TransposedConvBinWinoRxS<3-2>:18
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+1
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:22;TransposedConvBinWinoRxS<3-2>:66
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:109
2x64x56x56x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:15;TransposedConvBinWinoRxS<3-2>:8
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,91;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:7;TransposedConvBinWinoRxS<3-2>:128
2x64x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:9;TransposedConvBinWinoRxS<3-2>:11
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:250
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:13;TransposedConvBinWinoRxS<3-2>:12
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:17
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:229
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:52
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:209
2x64x56x56x1x1x1x1x64x35x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:19
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:106;TransposedConvBinWinoRxS<3-2>:37
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x64x408x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:46
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,121[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,147[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:245
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:8;TransposedConvBinWinoRxS<3-2>:7
2x64x56x56x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:66
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;TransposedConvBinWinoRxS<3-2>:245
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:34
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;TransposedConvBinWinoRxS<3-2>:240
2x64x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:4;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:106
2x64x56x56x1x1x1x1x64x624x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];TransposedConvBinWinoRxS<2-3>:9;TransposedConvBinWinoRxS<3-2>:11
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];TransposedConvBinWinoRxS<2-3>:6;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:191
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];TransposedConvBinWinoRxS<2-3>:46;TransposedConvBinWinoRxS<3-2>:10
2x64x56x56x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];TransposedConvBinWinoRxS<2-3>:5;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x56x56x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x2x2x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x192x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x464x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x56x56x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:23;TransposedConvBinWinoRxS<3-2>:15
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x56x56x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x1024x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x11x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:241
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:247
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:6
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:38
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+128
2x64x56x56x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:189
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:82;TransposedConvBinWinoRxS<3-2>:15
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:172
2x64x56x56x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];TransposedConvBinWinoRxS<2-3>:31;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:207
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:181
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:185
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:26;TransposedConvBinWinoRxS<3-2>:14
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:183
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,213[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x204x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:251
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:251
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];TransposedConvBinWinoRxS<2-3>:74;TransposedConvBinWinoRxS<3-2>:73
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x3x3x1x64x208x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];TransposedConvBinWinoRxS<2-3>:22;TransposedConvBinWinoRxS<3-2>:61
2x64x56x56x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x21x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x22x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[6];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];TransposedConvBinWinoRxS<2-3>:37;TransposedConvBinWinoRxS<3-2>:15
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];TransposedConvBinWinoRxS<2-3>:23;TransposedConvBinWinoRxS<3-2>:10
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];TransposedConvBinWinoRxS<2-3>:37;TransposedConvBinWinoRxS<3-2>:70
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x3x3x1x64x312x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];TransposedConvBinWinoRxS<2-3>:24;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:246
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];TransposedConvBinWinoRxS<2-3>:45;TransposedConvBinWinoRxS<3-2>:8
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];TransposedConvBinWinoRxS<3-2>:248
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x352x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x352x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:204
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:25;TransposedConvBinWinoRxS<3-2>:12
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:205
2x64x56x56x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:5
2x64x56x56x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];TransposedConvBinWinoRxS<2-3>:33;TransposedConvBinWinoRxS<3-2>:125
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:249
2x64x56x56x1x3x3x1x64x408x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];TransposedConvBinWinoRxS<2-3>:21;TransposedConvBinWinoRxS<3-2>:11
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x464x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x64x56x56x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x464x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x64x56x56x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:241
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];TransposedConvBinWinoRxS<2-3>:24;TransposedConvBinWinoRxS<3-2>:109
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];TransposedConvBinWinoRxS<2-3>:24;TransposedConvBinWinoRxS<3-2>:39
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:243
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];TransposedConvBinWinoRxS<2-3>:26;TransposedConvBinWinoRxS<3-2>:8
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:238
2x64x56x56x1x3x3x1x64x51x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[9];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=TransposedConvBinWinoRxS<3-2>:252
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:253
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];TransposedConvBinWinoRxS<2-3>:23;TransposedConvBinWinoRxS<3-2>:128
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;TransposedConvBinWinoRxS<3-2>:254
2x64x56x56x1x3x3x1x64x624x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];TransposedConvBinWinoRxS<2-3>:21;TransposedConvBinWinoRxS<3-2>:9
2x64x56x56x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x56x56x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:255
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:242
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:244
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:8
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;TransposedConvBinWinoRxS<3-2>:242
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x56x56x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:195
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:204
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:188
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:35;TransposedConvBinWinoRxS<3-2>:16
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];TransposedConvBinWinoRxS<3-2>:214
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:5
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x56x56x1x3x3x1x64x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x2xNCHWxFP32xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP16xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xB=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x56x56x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x4xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2
2x64x56x56x1x7x7x1x3x1024x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x56x56x1x7x7x1x3x128x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x256x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x352x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x352x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x464x2x2x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x464x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x56x56x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x56x56x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x56x56x1x7x7x1x64x4x3x3x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x575x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x575x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x576x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x576x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x576x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x576x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x579x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x579x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x579x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x579x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x57x57x1x11x11x1x3x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x1024x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x128x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x57x57x1x11x11x1x3x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x57x57x1x11x11x1x3x1x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x256x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x2x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x2x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x32x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
2x64x57x57x1x11x11x1x3x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x4x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,10,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x512x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x11x11x1x3x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x57x57x1x11x11x1x3x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x57x57x1x11x11x1x3x8x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,46;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x64x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[3];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x57x57x1x3x3x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x57x57x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x57x57x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x57x57x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x57x57x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x57x57x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x57x57x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x57x57x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x64x57x57x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x64x57x57x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x57x57x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x57x57x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x57x57x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x57x57x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x57x57x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x57x57x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x64x57x57x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x57x57x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x57x57x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x57x57x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x587x587x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x587x587x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x587x587x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x587x587x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x587x587x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x587x587x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x588x588x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x589x589x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x589x589x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x589x589x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x591x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x591x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x591x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x591x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x592x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x592x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x592x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x592x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x592x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x592x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x595x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x595x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x595x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x595x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x595x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x595x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x597x597x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x597x597x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x597x597x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x597x597x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x597x597x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x5x5x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 4, 1, 2, 1, 1, 1>+128
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x600x600x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8]
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x600x600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x600x600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x600x600x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 4, 1, 2, 1, 1, 1>+-1
2x64x600x600x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x600x600x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x600x600x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9]
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x600x600x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x600x600x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x600x600x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x112x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x114x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x603x603x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 4, 1, 2, 1, 1, 1>+-1
2x64x603x603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x603x603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x603x603x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x603x603x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x603x603x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x603x603x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 4, 1, 2, 1, 1, 1>+128
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x64x603x603x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x603x603x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x603x603x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x608x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x608x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x608x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x608x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x611x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x611x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x611x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x611x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x623x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x623x335x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x623x367x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x623x367x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x624x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x624x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x624x368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x624x368x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x627x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x627x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x627x371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x627x371x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x639x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x639x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x639x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x639x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x640x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x640x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x640x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x640x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x643x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+2
2x64x643x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x643x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x643x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x64x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x64x128x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x64x128x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x64x128x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x64x64x128x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x64x128x1x5x5x1x24x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,315[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x64x128x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x64x64x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x64x64x1x1x1x1x196x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x1x1x1x1x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,64[1];ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x64x64x64x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x64x64x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x64x64x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x64x64x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x64x64x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x64x64x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x64x64x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x64x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x3x3x1x3x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x64x64x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x64x64x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x64x64x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x64x64x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x64x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[2];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x64x64x1x7x7x1x64x1x3x3x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x64x655x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x655x319x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x655x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x655x351x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x656x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x656x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x656x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x656x352x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x659x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x659x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x659x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x659x355x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x672x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x672x320x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x672x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x672x336x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x675x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x675x323x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x675x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x675x339x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x69x69x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x69x69x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x69x69x1x3x3x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x69x69x1x3x3x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x69x69x1x3x3x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x69x69x1x3x3x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x69x81x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x69x81x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x6x60x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x6x60x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x6x60x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x6x60x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x6x60x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x6x60x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x6x60x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x6x60x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x6x60x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,16,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,71[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x6x60x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x6x60x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x6x60x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x71x71x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x71x71x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x71x71x1x3x3x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x71x71x1x3x3x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x71x71x1x3x3x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x71x71x1x3x3x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x71x71x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x71x71x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x71x71x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x71x71x1x3x3x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x71x77x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x71x77x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x71x77x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x64x73x73x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,204[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x73x73x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x64x73x73x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x64x73x73x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x73x73x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x73x73x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x64x73x73x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x64x73x73x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,202[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,110[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+128
2x64x73x73x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x64x73x73x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x73x73x1x1x1x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x1x1x80x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x1x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x1x1x80x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,171[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x256x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+128
2x64x73x73x1x1x7x1x64x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x1x7x1x64x2x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x1x7x1x64x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x512x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x1x7x1x64x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x73x73x1x1x7x1x64x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x6x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x1x7x1x64x8x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x73x73x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x80x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x80x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,59[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x3x3x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x73x73x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x16x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x7x1x1x64x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x7x1x1x64x2x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x64x73x73x1x7x1x1x64x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x73x73x1x7x1x1x64x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x73x73x1x7x1x1x64x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x73x73x1x7x1x1x64x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x7x1x1x64x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x7x1x1x64x512x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x73x73x1x7x1x1x64x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x73x73x1x7x1x1x64x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x6x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x73x73x1x7x1x1x64x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x75x75x1x1x1x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x100x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:251
2x64x75x75x1x1x1x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x112x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x64x75x75x1x1x1x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:247
2x64x75x75x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x200x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:256
2x64x75x75x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:50
2x64x75x75x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:252
2x64x75x75x1x1x1x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,151;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,65;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x3x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,132;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:94
2x64x75x75x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:253
2x64x75x75x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x1x1x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x58x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x1x1x128x59x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:228
2x64x75x75x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x64x75x75x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x1x3x1x64x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x3x1x64x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x1x3x1x64x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x1x3x1x64x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x3x1x64x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x3x1x64x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x1x3x1x64x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x1x3x1x64x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x64x75x75x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x1x1x64x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x1x1x64x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x1x1x64x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x1x1x64x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x1x1x64x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x1x1x64x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x1x1x64x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x100x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:255
2x64x75x75x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:252
2x64x75x75x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x200x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:256
2x64x75x75x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:44
2x64x75x75x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:239
2x64x75x75x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x128x3x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:118
2x64x75x75x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>;TransposedConvBinWinoRxS<3-2>:253
2x64x75x75x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x58x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x59x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x75x75x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:243
2x64x75x75x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x10x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x10x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:245
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:251
2x64x75x75x1x3x3x1x64x112x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:6
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:240
2x64x75x75x1x3x3x1x64x114x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:6
2x64x75x75x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x11x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x11x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:252
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:9
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:254
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[5];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:253
2x64x75x75x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[7];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:6
2x64x75x75x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x12x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x12x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x13x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x13x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x14x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x14x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x15x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x15x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x16x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x16x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x17x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x17x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x75x75x1x3x3x1x64x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x18x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x18x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x75x75x1x3x3x1x64x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x19x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x19x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x64x75x75x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x75x75x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x64x1x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x1x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[3];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x20x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x20x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x21x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x21x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x22x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x22x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x23x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x23x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:244
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];TransposedConvBinWinoRxS<2-3>:30;TransposedConvBinWinoRxS<3-2>:21
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;TransposedConvBinWinoRxS<3-2>:243
2x64x75x75x1x3x3x1x64x24x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:7
2x64x75x75x1x3x3x1x64x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x24x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x24x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:251
2x64x75x75x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[6];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:123
2x64x75x75x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x25x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x25x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x26x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x26x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x27x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x27x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x28x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x28x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x29x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x29x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,231[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:101
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236
2x64x75x75x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:17;TransposedConvBinWinoRxS<3-2>:34
2x64x75x75x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x64x2x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x2x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x30x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x30x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x75x75x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x31x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x31x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:254
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x32x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x32x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x33x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x33x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x34x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x34x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x35x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x35x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x36x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x36x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x64x75x75x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x37x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x37x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,88[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:151
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];TransposedConvBinWinoRxS<2-3>:16;TransposedConvBinWinoRxS<3-2>:4
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];TransposedConvBinWinoRxS<3-2>:129
2x64x75x75x1x3x3x1x64x3x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];TransposedConvBinWinoRxS<2-3>:27;TransposedConvBinWinoRxS<3-2>:4
2x64x75x75x1x3x3x1x64x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x64x3x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x3x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:192
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277
2x64x75x75x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;TransposedConvBinWinoRxS<3-2>:164
2x64x75x75x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x4x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x4x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:255
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,107[3];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:250
2x64x75x75x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[10];TransposedConvBinWinoRxS<2-3>:18;TransposedConvBinWinoRxS<3-2>:127
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:244
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:248
2x64x75x75x1x3x3x1x64x56x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];TransposedConvBinWinoRxS<2-3>:67;TransposedConvBinWinoRxS<3-2>:5
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x58x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x5x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x5x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:253
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,199
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;TransposedConvBinWinoRxS<3-2>:251
2x64x75x75x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[2];TransposedConvBinWinoRxS<2-3>:47;TransposedConvBinWinoRxS<3-2>:8
2x64x75x75x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x6x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x6x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x7x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x7x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x8x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x8x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x75x75x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x75x75x1x3x3x1x64x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x75x75x1x3x3x1x64x9x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x75x75x1x3x3x1x64x9x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x768x768x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x64x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, OddC, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x64x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
2x64x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85
2x64x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x114x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x120x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,49;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,57;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x76x76x1x1x1x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,53;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x76x76x1x1x1x1x128x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,67[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x76x76x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x76x76x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x76x76x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x77x347x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x77x347x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x77x347x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,1,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x77x347x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x77x347x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x77x71x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x77x71x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x77x71x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x77x71x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x77x71x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x77x71x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x77x77x1x3x3x1x128x114x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x77x77x1x3x3x1x128x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x77x77x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x77x77x1x3x3x1x128x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x77x77x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x77x77x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x77x77x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x77x77x1x3x3x1x128x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x77x77x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x78x348x1x5x5x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x78x348x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x78x348x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x348x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8]
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x79x349x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x79x349x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x79x349x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x79x349x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x79x349x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x79x349x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x79x349x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x79x349x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x79x349x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x79x349x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x7x7x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x7x7x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x64x80x349x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x349x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x80x349x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x80x350x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[10]
2x64x80x350x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x64x80x350x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,197[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,85;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,105[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,301;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,193;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x80x350x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x80x350x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7]
2x64x80x350x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x80x350x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x64x80x350x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x80x350x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x80x350x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x80x350x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x80x350x1x5x5x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x80x350x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x81x349x1x5x5x1x1x1024x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x1024x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x16x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x1x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x256x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x2x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x32x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x4x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x349x1x5x5x1x1x512x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x512x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8]
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x64x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x349x1x5x5x1x1x8x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x350x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[10]
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x64x81x350x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[8]
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+2
2x64x81x350x1x5x5x1x1x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,51[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x64x81x351x1x5x5x1x128x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x81x351x1x5x5x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x64x81x351x1x5x5x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x81x351x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x64x81x69x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x64x81x69x1x3x3x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x81x69x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x81x69x1x3x3x1x64x32x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x64x833x833x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x833x833x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[3]
2x64x833x833x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x833x833x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38
2x64x833x833x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x833x833x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10]
2x64x833x833x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x833x833x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7]
2x64x834x834x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x834x834x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x834x834x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x834x834x1x3x3x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4>+-1
2x64x834x834x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x834x834x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x834x834x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x64x834x834x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+-1
2x64x836x836x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x836x836x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x836x836x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x836x836x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x837x837x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x837x837x1x3x3x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x837x837x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x837x837x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x88x88x1x3x3x1x128x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x64x88x88x1x8x8x1x64x4x0x0x0x8x8x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x8x8x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,2,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x64x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x64x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x64x912x1144x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x64x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x912x1144x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x912x1144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x912x1144x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x64x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x64x912x1144x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x64x96x96x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x96x96x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x96x96x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x96x96x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,152;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x64x96x96x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x64x96x96x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x64x96x96x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x64x96x96x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x96x96x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x96x96x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x654x128x128x1x1x1x1x123x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x654x1x1x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x65x256x256x1x1x1x1x390x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x65x28x28x1x1x1x1x390x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x664x64x64x1x3x3x1x664x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x664x7x7x1x1x1x1x2656x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x6656x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x66x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x66x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x66x1x30x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+4
2x66x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+4
2x66x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x66x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x66x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x66x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x66x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x66x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x66x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+4
2x66x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+4
2x66x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+2
2x66x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x66x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x66x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x66x1x30x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x66x1x30x1x1x1x1x66x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x66x1x30x1x1x1x1x66x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x66x1x30x1x1x1x1x66x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x66x1x30x1x1x1x1x66x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x66x1x30x1x1x1x1x66x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x672x11x11x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x11x11x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x672x11x11x1x1x1x1x4032x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x672x11x11x1x1x1x1x4032x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x672x11x11x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x11x11x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x672x11x11x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x11x11x1x3x3x1x672x64x1x1x0x1x1x0x1x1x0x0x672xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x672x11x11x1x3x3x1x672x64x1x1x0x1x1x0x1x1x0x0x672xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x672x11x11x1x3x3x1x672x64x1x1x0x1x1x0x1x1x0x0x672xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x672x11x11x1x5x5x1x672x64x2x2x0x1x1x0x1x1x0x0x672xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x672x11x11x1x5x5x1x672x64x2x2x0x1x1x0x1x1x0x0x672xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x672x11x11x1x5x5x1x672x64x2x2x0x1x1x0x1x1x0x0x672xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x672x11x11x1x5x5x1x672x64x2x2x0x2x2x0x1x1x0x0x672xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x672x11x11x1x5x5x1x672x64x2x2x0x2x2x0x1x1x0x0x672xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x672x11x11x1x7x7x1x672x64x3x3x0x1x1x0x1x1x0x0x672xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x672x11x11x1x7x7x1x672x64x3x3x0x1x1x0x1x1x0x0x672xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x11x11x1x7x7x1x672x64x3x3x0x1x1x0x1x1x0x0x672xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x672x11x11x1x7x7x1x672x64x3x3x0x2x2x0x1x1x0x0x672xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x672x11x11x1x7x7x1x672x64x3x3x0x2x2x0x1x1x0x0x672xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x672x128x128x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x128x128x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x128x128x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x128x128x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x672x128x128x1x3x3x1x672x1x1x1x0x2x2x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x128x128x1x5x5x1x672x4x2x2x0x1x1x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x672x129x129x1x3x3x1x672x1x0x0x0x2x2x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x672x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:92;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x672x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[6];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x672x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x336x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x14x14x1x3x3x1x672x4x1x1x0x2x2x0x1x1x0x0x42xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x14x14x1x5x5x1x672x1x2x2x0x1x1x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x19x19x1x5x5x1x672x4x0x0x0x2x2x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x1x1x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x1x1x1x1x1x1x28x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x672x1x1x1x1x1x1x28x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x1x1x1x1x1x1x28x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[7];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x672x1x1x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x1x1x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x672x1x1x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x1x1x1x1x1x1x28x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x672x21x21x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x672x21x21x1x1x1x1x1344x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[10];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+4
2x672x21x21x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x672x21x21x1x1x1x1x2016x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[8];ConvBinWinogradRxSf2x3:190;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x672x21x21x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x21x21x1x5x5x1x672x64x2x2x0x2x2x0x1x1x0x0x672xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x21x21x1x7x7x1x672x64x3x3x0x2x2x0x1x1x0x0x672xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x24x24x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x256x256x1x1x1x1x1344x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x256x256x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x256x256x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x1344x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x32x32x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x672x32x32x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x32x32x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x672x32x32x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x672x32x32x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x32x32x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x672x32x32x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x32x32x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x32x32x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x32x32x1x3x3x1x672x1x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x32x32x1x5x1x1x672x1x2x0x0x1x1x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x48x32x1x1x1x1x576x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x48x32x1x1x1x1x576x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x48x32x1x1x1x1x576x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x48x32x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x672x48x32x1x1x1x1x576x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x512x512x1x3x3x1x672x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x672x512x512x1x3x3x1x672x4x1x1x0x2x2x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x64x64x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x64x64x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x64x64x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x64x64x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x64x64x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x64x64x1x1x1x1x672x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x64x64x1x3x3x1x672x1x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x672x64x64x1x5x1x1x672x1x2x0x0x1x1x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x672x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x672x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x672x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x672x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x672x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x672x7x7x1x3x3x1x672x4x1x1x0x1x1x0x1x1x0x0x42xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x672x7x7x1x7x7x1x672x1x3x3x0x1x1x0x1x1x0x0x672xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x672x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x67x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x128x128x1x1x1x1x201x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x67x128x128x1x1x1x1x201x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x67x128x128x1x1x1x1x213x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x67x14x14x1x1x1x1x213x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x67x48x32x1x1x1x1x64x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x48x32x1x1x1x1x64x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x67x64x64x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x68x128x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x68x128x128x1x3x3x1x68x4x1x1x0x1x1x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x68x14x14x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x68x14x14x1x3x3x1x68x1x1x1x0x1x1x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x68x1x1x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+4
2x68x1x1x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x68x1x1x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x68x1x1x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x68x1x1x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,3,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x68x1x1x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x68x1x1x1x1x1x1x1632x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[5];ConvBinWinogradRxSf2x3:188;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x68x256x256x1x3x3x1x68x1x1x1x0x2x2x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x68x28x28x1x1x1x1x44x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x68x28x28x1x3x3x1x68x1x1x1x0x1x1x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x68x28x28x1x3x3x1x68x1x1x1x0x2x2x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x68x28x28x1x3x3x1x68x4x1x1x0x2x2x0x1x1x0x0x68xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x68x64x64x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x696x128x128x1x1x1x1x149x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x696x128x128x1x1x1x1x696x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x696x128x128x1x3x3x1x696x1x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x696x256x256x1x1x1x1x1392x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x696x256x256x1x1x1x1x149x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x696x256x256x1x3x3x1x696x1x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x696x256x256x1x3x3x1x696x1x1x1x0x2x2x0x1x1x0x0x696xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x696x256x256x1x3x3x1x696x4x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x696x28x28x1x1x1x1x1392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x696x28x28x1x1x1x1x1392x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x696x28x28x1x3x3x1x696x4x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x696x512x512x1x3x3x1x696x1x1x1x0x2x2x0x1x1x0x0x696xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x696x512x512x1x3x3x1x696x4x1x1x0x2x2x0x1x1x0x0x696xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x696x56x56x1x3x3x1x696x4x1x1x0x2x2x0x1x1x0x0x696xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x69x1x1x1x1x1x1x828x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x69x512x512x1x3x3x1x69x4x1x1x0x1x1x0x1x1x0x0x69xNCHWxFP16xF=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x6x10x10x1x5x5x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:250
2x6x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:181;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1]
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x128x128x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x14x14x1x5x5x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x14x14x1x5x5x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x14x14x1x5x5x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x6x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x16x16x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x6x16x16x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x16x16x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x6x16x16x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x6x16x16x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x16x16x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>+1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x6x16x16x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x16x16x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x6x16x16x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x6x16x16x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x6x1x1x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+2
2x6x1x1x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x144x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:186;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+4
2x6x1x1x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+2
2x6x1x1x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x6x1x1x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+1
2x6x1x1x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x6x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,1,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>+2
2x6x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+2
2x6x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x6x1x1x1x1x1x1x56x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x62x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x6x1x1x1x1x1x1x62x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x6x1x1x1x1x1x1x70x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,1,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x24x24x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x6x256x256x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+128
2x6x256x256x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x6x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x256x256x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x256x256x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:64
2x6x256x256x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x256x256x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[10]
2x6x256x256x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[6];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x256x256x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x256x256x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[1];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x28x28x1x5x5x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x6x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x6x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x6x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x6x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x32x32x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x6x32x32x1x5x5x1x3x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x6x32x32x1x5x5x1x3x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x6x64x64x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x6x64x64x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x6x64x64x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x64x64x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x6x64x64x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x64x64x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:242
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,230[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,4,32,32,2,1,1,2,2,1,0,0,1,0,1,1,2,1,1,4,1,64,1,1,2,1,1,4,1,64,20;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x64x64x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:179;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x6x64x64x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x6x64x64x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x6x64x64x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x702x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x702x1x1x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x704x111x111x1x1x1x1x1072x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x704x112x112x1x1x1x1x1072x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x704x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x128x128x1x5x5x1x704x1x2x2x0x1x1x0x1x1x0x0x704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x704x128x128x1x7x7x1x704x1x3x3x0x1x1x0x1x1x0x0x704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x704x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x704x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x704x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x704x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x704x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x704x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x704x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x256x256x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x704x256x256x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x256x256x1x2x2x1x1408x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x704x256x256x1x3x3x1x1408x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x256x256x1x7x7x1x704x1x3x3x0x1x1x0x1x1x0x0x704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x704x27x27x1x1x1x1x1072x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x28x28x1x1x1x1x1072x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x28x28x1x1x1x1x1413x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x704x28x28x1x1x1x1x1413x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x704x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x28x28x1x1x1x1x704x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x28x28x1x1x1x1x704x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x28x28x1x3x3x1x1408x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x28x28x1x3x3x1x704x4x1x1x0x1x1x0x1x1x0x0x704xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x704x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x64x64x1x1x1x1x2816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x7x7x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x1024x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x704x7x7x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x704x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:89;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x704x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:90;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x704x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x704x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:98;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x704x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[1];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x704x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x704x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x704x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x704x7x7x1x1x1x1x2816x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x70x1x1x1x1x1x1x840x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x70x256x256x1x1x1x1x35x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x70x515x515x1x5x5x1x70x1x0x0x0x2x2x0x1x1x0x0x70xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x70x515x515x1x5x5x1x70x4x0x0x0x2x2x0x1x1x0x0x70xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x70x59x59x1x5x5x1x70x1x0x0x0x2x2x0x1x1x0x0x70xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x719x32x32x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x719x64x64x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x719x7x7x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x71x1x1x1x1x1x1x852x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x71x1x1x1x1x1x1x852x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x720x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x100x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x100x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x100x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x100x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x100x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x100x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x100x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x100x136x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x100x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x100x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x100x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x720x100x152x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x100x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x100x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x100x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x100x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x100x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x100x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x100x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x100x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x100x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x104x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x104x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x104x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x104x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x104x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x108x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x108x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x108x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x108x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x108x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x108x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x108x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x108x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x108x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x108x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x108x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x720x10x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x10x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x18x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x10x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x10x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x10x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x720x10x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x10x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x112x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x112x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x112x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x112x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x112x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x112x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x112x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x112x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x116x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x116x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x116x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x116x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x11x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x11x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>+32
2x720x11x17x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x11x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x11x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x11x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x11x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x720x11x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x120x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x120x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x120x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x120x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x120x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x120x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x120x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x120x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x120x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x124x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x124x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x124x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x124x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x124x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x124x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x124x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x124x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x124x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x128x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x128x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x128x128x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x720x128x128x1x3x3x1x720x1x1x1x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x128x128x1x3x3x1x720x4x1x1x0x1x1x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x720x128x128x1x5x5x1x720x4x2x2x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x128x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x128x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x128x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x128x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x128x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x128x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x128x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x128x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x12x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x12x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x12x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x12x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x12x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x12x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x132x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x132x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x132x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x132x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x132x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x136x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x720x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x136x88x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x136x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x13x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x13x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x17x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x19x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x13x19x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x13x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x13x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x13x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x140x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x140x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x140x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x144x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x144x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x144x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x144x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x144x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x144x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x144x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x144x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x144x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x144x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x148x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x148x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x148x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x148x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x148x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x14x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x14x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x14x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x14x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x14x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x14x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x14x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x1920x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x1920x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x720x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x720x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x720x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x720x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x720x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x720x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x720x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x720x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x720x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x720x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x14x14x1x3x3x1x720x1x1x1x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x14x14x1x5x5x1x720x1x2x2x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x14x14x1x5x5x1x720x4x2x2x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x152x100x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x152x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x152x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x152x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x152x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+8
2x720x152x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x152x96x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x152x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,9,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[9];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x156x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x720x156x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x156x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x156x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x156x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x156x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x156x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x15x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x15x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x15x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x15x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x15x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x15x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x15x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x160x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x160x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x160x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x160x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x160x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x160x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x160x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x164x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x164x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x164x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x164x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x164x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x164x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x164x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x164x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x168x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x168x100x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x168x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x720x168x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Default, 32, 32, 2, 2, 4, 2, 1, 1>+8
2x720x168x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x720x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x168x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,7,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x168x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x168x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x168x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x16x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x720x16x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x720x16x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x16x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x16x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x16x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x16x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x16x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x17x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x17x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x17x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x17x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x17x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x18x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x18x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x18x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x18x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x18x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x18x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x19x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x19x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x19x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x19x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x19x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x19x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x1x1x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x1x1x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x1x1x1x1x1x1x30x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x20x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x20x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x20x27x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[4];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,5,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x20x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x20x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x20x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x720x20x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x20x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x20x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x20x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x20x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x20x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x20x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x21x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x21x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x12x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x21x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x720x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x21x26x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x21x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x21x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x720x21x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x21x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x21x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x21x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x21x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x21x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x21x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[9];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x21x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x21x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x21x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x22x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[8];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x22x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x22x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x30x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x22x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x22x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x33x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x22x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x22x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x22x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x22x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x22x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x22x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x22x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x22x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x22x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x22x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x23x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x23x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x23x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x23x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x23x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x23x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x23x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x23x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x31x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x23x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x23x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x23x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x35x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x23x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x23x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x23x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x23x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x23x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x23x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x24x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x26x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x24x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x24x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x29x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x24x30x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x24x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x24x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x24x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x36x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x24x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x39x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x24x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x24x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x24x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x25x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x25x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x25x28x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x25x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x25x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x31x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x33x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x34x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x720x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x34x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x25x36x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x38x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x25x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x25x39x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x25x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x41x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x25x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x41x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x25x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x25x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x26x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x26x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x26x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x26x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x26x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x27x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,43[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x27x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x27x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x27x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x27x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x27x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x27x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x27x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x27x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x27x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x28x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x28x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x28x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x28x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x28x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x28x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x720x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x720x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x28x28x1x3x3x1x720x4x1x1x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x29x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x720x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x29x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x29x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x29x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x29x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x29x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x30x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x30x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x30x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x30x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x30x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x30x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x30x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x31x20x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x31x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x31x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x31x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x31x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x31x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x31x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x31x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x31x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x32x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x32x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x32x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+1
2x720x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x32x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x32x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x32x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x32x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x32x32x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x32x32x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x720x33x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x33x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x33x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x33x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x33x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x33x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x33x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x34x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x34x22x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x34x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x34x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x34x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x34x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x35x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x35x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x35x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x35x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x35x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x35x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x35x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x36x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x36x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x36x23x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x36x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x36x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x36x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x36x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x36x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x36x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x37x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x37x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x38x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x38x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x38x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x38x24x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x720x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x38x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x38x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x720x38x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x38x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x39x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x39x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x39x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x39x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x39x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x39x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,39[8];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x40x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x40x54x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x40x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x40x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x40x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x40x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x40x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x40x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x40x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x40x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x40x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x40x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x41x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x41x22x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x41x23x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x41x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x41x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x720x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x21x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x25x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x52x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x42x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x42x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x42x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x42x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x42x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x42x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x42x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x42x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x42x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x42x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x42x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x42x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x42x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x42x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x44x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x44x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x44x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x44x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x44x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x44x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x44x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x44x60x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x44x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x44x62x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x44x66x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x44x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x44x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x720x44x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x44x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x44x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x44x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x46x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x46x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x46x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x46x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x46x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x46x62x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x46x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x46x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x46x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x46x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x46x70x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x46x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x46x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x46x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x46x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x46x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x46x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x46x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x46x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x46x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x46x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x46x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x46x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x46x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x48x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x48x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x48x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x48x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x48x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x48x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x48x56x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x48x58x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x48x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x48x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x48x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x48x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x48x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x48x72x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x48x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x48x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x48x74x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x48x76x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x48x78x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x48x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x48x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x48x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x48x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x48x82x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x48x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x48x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x48x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x50x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x50x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x50x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x50x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x50x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x50x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x50x54x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x50x70x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x50x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x50x72x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x50x74x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x50x76x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x50x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x50x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x50x82x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x52x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x52x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x52x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x52x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x52x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x52x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x52x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x52x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x52x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x52x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x54x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x54x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x54x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x54x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x54x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x54x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x54x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x54x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x56x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x56x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x56x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x56x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x56x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x56x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x56x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x58x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x58x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x58x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x58x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x58x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x58x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x720x5x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x5x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x5x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x720x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x720x5x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x5x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x5x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x5x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x5x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x720x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x60x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x60x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x60x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x60x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[5];ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x62x40x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x62x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x62x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x62x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x62x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x62x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x64x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x64x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x64x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x64x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x64x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x64x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x64x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x64x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x64x64x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x64x64x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x64x64x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x64x64x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x64x64x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x720x65x65x1x3x3x1x720x1x0x0x0x2x2x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x66x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x66x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x66x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x66x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x66x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x66x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x66x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x68x44x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x68x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x720x6x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x11x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x720x6x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x8x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x720x6x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x6x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x70x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x70x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x70x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x70x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x70x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x70x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x70x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x70x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x70x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x70x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x70x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x70x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x72x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x72x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x72x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x72x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x72x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x72x46x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x72x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x72x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x72x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x74x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[3];ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x74x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x74x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x74x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x74x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x76x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x76x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x720x76x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x76x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x76x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
2x720x76x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x76x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x78x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x78x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x78x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x78x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+2
2x720x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x10x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x10x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x11x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x7x7x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x7x7x1x1x1x1x208x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x7x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x720x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x8x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x720x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x7x9x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x720x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x80x108x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x80x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x80x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x80x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+16
2x720x80x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x80x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x80x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x80x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+8
2x720x80x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x80x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x80x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x80x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x80x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x80x44x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x80x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x80x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x80x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x80x80x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x80x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x80x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x82x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x82x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x82x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x82x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x82x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x84x104x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x84x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x84x112x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x84x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x84x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x84x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x84x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x84x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x84x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x84x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x84x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x84x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+4
2x720x84x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x84x40x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x720x84x42x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x84x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x84x46x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x720x84x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x84x48x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x720x84x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x84x50x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x84x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x84x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x88x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x720x88x108x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x88x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x88x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x88x120x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x88x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x88x132x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,19[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x88x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x88x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x720x88x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x88x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x88x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x88x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x88x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x8x5x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x8x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x8x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x8x7x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,38;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x92x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x92x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x720x92x124x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x92x124x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x92x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x92x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x92x136x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x92x140x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x92x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x92x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 16, 4, 4, Default, 32, 32, 4, 2, 4, 2, 1, 1>+16
2x720x92x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x720x92x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x92x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x92x156x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x92x164x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x92x164x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x720x92x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x92x168x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Default, 32, 32, 2, 4, 4, 4, 1, 1>+4
2x720x92x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x92x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x720x92x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19[4];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x92x92x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x92x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x112x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x96x116x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x96x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x96x116x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x720x96x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x96x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x132x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x144x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+4
2x720x96x144x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+8
2x720x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x720x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x96x148x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+2
2x720x96x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x160x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
2x720x96x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,54;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x96x160x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[6];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x720x96x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,128,16,32,32,2,2,1,2,2,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,8,1,16,1,16,3[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x720x96x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
2x720x96x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x96x88x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,6,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,15[6];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x96x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x720x96x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x720x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x720x9x21x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x9x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x9x5x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,6,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[6];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+32
2x720x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x9x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[6];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+32
2x720x9x6x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,22;ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+64
2x720x9x7x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,42;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x720x9x9x1x3x3x1x720x1x0x0x0x1x1x0x1x1x0x0x720xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x726x1x1x1x1x1x1x7392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x728x128x128x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x728x128x128x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x728x128x128x1x1x1x1x728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x728x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x728x14x14x1x3x3x1x728x4x1x1x0x1x1x0x1x1x0x0x728xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x728x256x256x1x1x1x1x728x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x728x256x256x1x1x1x1x728x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x728x28x28x1x1x1x1x728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x728x64x64x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x72x1024x1024x1x1x1x1x72x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x72x1024x1024x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x1024x1024x1x3x3x1x72x4x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x72x112x112x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x112x112x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x112x112x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x112x112x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x128x128x1x1x1x1x18x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x128x128x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x128x128x1x1x1x1x360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x128x128x1x1x1x1x42x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x128x128x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x128x128x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x72x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x1x1x1x360x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x1x1x1x36x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,281;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x14x14x1x1x1x1x432x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x72x14x14x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x14x14x1x1x1x1x432x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,283;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x14x14x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x72x14x14x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x14x14x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvDepthwiseFwd2D:DeviceGroupedConvFwd<2, 64, BlockTileSize: 14, 14, FilterSize: 3,3, Dilation: 1, 1, Stride: 1, 1, Pad: 1, 1, NBatch: 32, SubTileH: 4, SubTileW: 4, InVectorWidth: 2, OutVectorWidth: 2, RequirePadding: 0>;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x14x14x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x14x14x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvDepthwiseFwd2D:DeviceGroupedConvFwd<2, 64, BlockTileSize: 14, 14, FilterSize: 3,3, Dilation: 1, 1, Stride: 1, 1, Pad: 1, 1, NBatch: 32, SubTileH: 4, SubTileW: 4, InVectorWidth: 2, OutVectorWidth: 2, RequirePadding: 0>;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x14x14x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x14x14x1x5x5x1x72x4x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x1x1x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x72x1x1x1x1x1x1x1728x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x1x1x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x1x1x1x1x1x1x280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x256x256x1x1x1x1x168x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x256x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x256x256x1x1x1x1x42x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x72x256x256x1x1x1x1x42x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x72x256x256x1x5x1x1x72x4x2x0x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x256x256x1x5x5x1x72x1x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x257x257x1x3x3x1x72x1x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x259x259x1x5x5x1x72x1x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:86;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x72x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x28x28x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x72x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x28x28x1x1x1x1x40x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x28x28x1x3x3x1x72x4x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x16x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x28x28x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x28x28x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x32x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x28x28x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x28x28x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x28x28x1x5x5x1x72x64x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x28x28x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x28x28x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x28x28x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x32x32x1x1x1x1x432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x512x512x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x512x512x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x512x512x1x1x1x1x168x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x72x512x512x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x72x512x512x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x512x512x1x3x3x1x72x1x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x512x512x1x3x3x1x72x1x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x512x512x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x72x512x512x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x512x512x1x7x7x1x72x4x3x3x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x513x513x1x3x3x1x72x4x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x515x515x1x5x5x1x72x4x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x168x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x168x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x216x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x72x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x72x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x16x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x56x56x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x16x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x72x56x56x1x3x3x1x72x2x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+128
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x32x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x72x56x56x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x32x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x72x56x56x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x72x56x56x1x3x3x1x72x4x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x4x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+16
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x72x56x56x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x16x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x1x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x32x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x4x2x2x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x5x5x1x72x64x2x2x0x2x2x0x1x1x0x0x72xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x7x7x1x72x4x3x3x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x9x9x1x72x4x4x4x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x57x57x1x3x3x1x72x1x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x72x64x64x1x1x1x1x18x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x72x64x64x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x72x64x64x1x3x3x1x72x1x1x1x0x1x1x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x66x66x1x1x1x1x432x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x732x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x732x128x128x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x732x1x1x1x1x1x1x61x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x732x28x28x1x3x3x1x732x4x1x1x0x2x2x0x1x1x0x0x732xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x736x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x736x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:97;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x736x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:94;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x736x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x736x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x256x256x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x736x256x256x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x736x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x32x32x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x32x32x1x1x1x1x328x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x64x64x1x1x1x1x184x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x64x64x1x1x1x1x184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x64x64x1x5x5x1x736x1x2x2x0x1x1x0x1x1x0x0x736xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x736x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x736x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x736x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x736x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x736x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x736x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x736x7x7x1x1x1x1x328x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x738x128x128x1x1x1x1x138x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x738x128x128x1x3x3x1x738x1x1x1x0x1x1x0x1x1x0x0x738xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x738x14x14x1x1x1x1x138x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x7392x128x128x1x3x3x1x7392x4x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x7392x14x14x1x3x3x1x7392x1x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x7392x14x14x1x3x3x1x7392x4x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x7392x32x32x1x1x1x1x7392x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x7392x64x64x1x3x3x1x7392x1x1x1x0x2x2x0x1x1x0x0x28xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x74x128x128x1x1x1x1x164x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x74x14x14x1x1x1x1x188x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x74x64x64x1x1x1x1x137x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x74x64x64x1x1x1x1x399x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x750x128x128x1x1x1x1x142x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 2, 2, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x750x14x14x1x3x3x1x750x1x1x1x0x1x1x0x1x1x0x0x750xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x750x64x64x1x3x3x1x750x1x1x1x0x1x1x0x1x1x0x0x750xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x75x256x256x1x1x1x1x450x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x75x28x28x1x1x1x1x450x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7680x64x64x1x3x3x1x7680x1x1x1x0x1x1x0x1x1x0x0x7680xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x7680x7x7x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x7680x7x7x1x3x3x1x7680x1x1x1x0x1x1x0x1x1x0x0x7680xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x1024x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x1024x4095x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x768x10x15x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x10x15x1x3x3x1x256x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x10x15x1x3x3x1x256x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,47[3];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x112x112x1x3x3x1x768x4x1x1x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x128x128x1x1x1x1x1541x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x768x128x128x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x768x128x128x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x768x128x128x1x1x1x1x90x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x128x128x1x1x1x1x90x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x128x128x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x3x3x1x1536x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x128x128x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x128x128x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x128x128x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x128x128x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x128x128x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x129x129x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x12x12x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x12x12x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x12x12x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x13x13x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x146x146x1x7x7x1x768x1x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x147x147x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x147x147x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x768x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x768x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x1552x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x768x14x14x1x1x1x1x1552x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x768x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x2560x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x2560x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x24xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x1x1x1x768x1x0x0x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x1x1x1x768x4x0x0x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x2x2x1x1536x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x1536x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x768x14x14x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+16
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x768x14x14x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x14x14x1x3x3x1x768x4x1x1x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+32
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x14x14x1x3x3x1x768x64x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x768x14x14x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x1x2x2x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x1x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x14x14x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x4x2x2x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x14x14x1x7x7x1x768x1x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x14x14x1x7x7x1x768x4x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x15x15x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x768x15x15x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x15x15x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x15x15x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x16x16x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x16x16x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x16x16x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x16x16x1x3x3x1x768x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x16x16x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x768x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x17x17x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,0,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,56;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x768x17x17x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x17x17x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x128x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x17x17x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x17x17x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,16,1,16,1,16,1,1,1,2,1,16,1,16,29[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x17x17x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[3];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x17x17x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,3,0,0,1,1,1,16,1,16,1,16,1,1,1,4,1,16,1,16,13[3];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x17x17x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x17x17x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x17x17x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x17x17x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x17x17x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[3];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x768x17x17x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[3];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x1x1000x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1000x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1000x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1000x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1001x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1001x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1001x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1001x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1004x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1004x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1004x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1004x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1004x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1006x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1006x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1006x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1006x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1008x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1008x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1008x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1008x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1009x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1009x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x100x1x1x1x1x1536x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x1536x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x1536x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x1536x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x768x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x1x1x768x251x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x100x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x100x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x100x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x100x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1011x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1011x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1011x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1011x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1012x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1012x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1012x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1012x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1013x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1013x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1014x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1014x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1014x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1014x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1015x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1015x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1015x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1015x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1016x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1016x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1016x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1016x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1018x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1018x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1018x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1018x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1019x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1019x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1019x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1019x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x101x1x1x1x1x1536x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x1x1x1536x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x1x1x768x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x101x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x101x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x101x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1020x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1020x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1020x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1020x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1021x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1021x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1022x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1022x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1023x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1023x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1026x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1026x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1026x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1026x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1027x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1027x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1027x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1027x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1028x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1029x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1029x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x102x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x102x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x102x1x1x3x1x80x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x102x1x1x3x1x80x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1030x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1030x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1031x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1031x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1033x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1033x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1034x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1034x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1035x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1035x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1036x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1036x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1037x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1037x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1038x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1038x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x103x1x1x1x1x1536x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x1536x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x1536x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x1536x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x768x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x1x1x768x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x103x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x103x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x103x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x103x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x103x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x103x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1040x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1040x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1041x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x1x1x1536x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x1x1x768x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1041x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1041x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1041x1x1x3x1x80x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1042x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1042x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1043x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1043x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1044x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1044x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1045x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1045x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1047x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1047x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1048x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1048x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1049x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1049x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x1x1x1536x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x1536x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x1536x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x1536x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x768x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x1x1x768x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x104x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x104x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x104x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x104x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x104x1x1x3x1x80x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x104x1x1x3x1x80x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1050x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1050x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1051x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1051x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1051x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1051x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1052x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1052x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1053x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1053x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1054x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1054x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1055x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1055x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1057x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1057x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1058x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1058x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1059x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1059x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x105x1x1x1x1x1536x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x1x1x1536x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x1x1x768x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x105x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x105x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x105x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1060x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1060x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1061x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1061x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1062x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1062x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1064x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1064x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1064x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1064x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1064x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1067x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1067x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1067x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1067x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1067x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1068x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1068x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1068x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1068x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x106x1x1x1x1x1536x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x1x1x1536x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x1x1x768x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x106x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x106x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x106x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1071x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1071x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1071x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1071x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1072x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1072x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1072x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1072x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1073x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1073x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1073x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1073x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1073x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1076x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x1x1x1536x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x1x1x768x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1076x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1077x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1077x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1077x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1077x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1078x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1078x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1078x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1078x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x107x1x1x1x1x1536x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x1x1x1536x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x1x1x768x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x107x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x107x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x107x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x107x1x1x3x1x80x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x107x1x1x3x1x80x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1081x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1081x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1081x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1081x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1082x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1082x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1082x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1082x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1084x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1084x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1084x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1084x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1085x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1085x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1085x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1085x1x1x3x1x80x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1087x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1087x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1087x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1087x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1088x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1088x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1088x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1088x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x108x1x1x1x1x1536x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x1x1x1536x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x1x1x768x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x108x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x108x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1090x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1090x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1090x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1090x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1091x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1091x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1093x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1093x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1093x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1093x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1094x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1094x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1094x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1094x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1095x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[3];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1095x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1095x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1095x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1095x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1096x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1096x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1096x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1096x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1097x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1097x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1097x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1097x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x109x1x1x1x1x1536x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x1536x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x1536x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x1536x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x768x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x1x1x768x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x109x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x109x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x109x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x109x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x109x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1101x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1101x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1101x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1101x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1102x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1102x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1102x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1102x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1103x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1103x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1103x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1103x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1103x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1107x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1107x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1107x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1107x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1109x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1109x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1109x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1109x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x110x1x1x1x1x1536x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x1536x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x1536x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x1536x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x768x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x1x1x768x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x110x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x110x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x110x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x110x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x110x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x110x1x1x3x1x80x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x110x1x1x3x1x80x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1111x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1111x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1111x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1111x1x1x3x1x80x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1112x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1112x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1112x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1112x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1114x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1114x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1114x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1114x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1115x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1115x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1115x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1115x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1116x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1116x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1116x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1116x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1117x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1117x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1118x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1118x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1118x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1118x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x111x1x1x1x1x1536x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x1x1x1536x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x1x1x768x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x111x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x111x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x111x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x111x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1121x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1121x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1121x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1121x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1122x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1122x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1122x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1122x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1123x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1123x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1123x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1123x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1126x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1126x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1128x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1128x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1128x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1128x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1129x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1129x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1129x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1129x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1129x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x112x1x1x1x1x1536x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x1x1x1536x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x1x1x768x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x112x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x112x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x112x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x112x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1130x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x1x1x1536x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1130x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1134x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1134x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1134x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1134x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1135x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1135x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1135x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1135x1x1x3x1x80x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1138x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1138x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1138x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1138x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1139x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1139x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x113x1x1x1x1x1536x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x1x1x1536x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x1x1x768x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x113x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x113x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x113x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1140x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1140x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1140x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1140x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1141x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1141x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1141x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1141x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1141x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1143x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1143x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1143x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1143x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1146x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1146x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1146x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1146x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1148x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1148x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1148x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1148x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1149x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1149x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1149x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1149x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x114x1x1x1x1x1536x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x1x1x1536x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x1x1x768x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x114x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x114x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x114x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x114x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x114x1x1x3x1x80x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x114x1x1x3x1x80x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1152x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1152x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1152x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1152x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1153x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1153x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1153x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1153x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1155x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1155x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1155x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1155x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1157x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1157x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1157x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1157x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1158x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1158x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1158x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1158x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1158x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1159x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1159x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x115x1x1x1x1x1536x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x1536x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x1536x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x1536x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x768x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x1x1x768x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x115x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x115x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x115x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x115x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x115x1x1x3x1x80x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x115x1x1x3x1x80x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1162x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1162x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1162x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1162x1x1x3x1x80x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1164x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1164x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1164x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1164x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1166x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1166x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1166x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1166x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1167x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1167x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1167x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1167x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1168x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1168x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1168x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1168x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x116x1x1x1x1x1536x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x1x1x1536x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x1x1x768x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x116x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x116x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x116x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1172x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1172x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1172x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1172x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1173x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1173x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1173x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1173x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1173x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1174x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1174x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1174x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1174x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1176x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1176x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1176x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1176x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x1179x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1179x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1179x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1179x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x117x1x1x1x1x1536x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x1536x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x1536x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x1536x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x768x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x1x1x768x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x117x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x117x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x117x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x117x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1180x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1180x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1180x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1180x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1183x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1183x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1183x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1183x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1185x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1185x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1185x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1185x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1186x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x1x1x1536x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x1x1x768x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1186x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1186x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1186x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x118x1x1x1x1x1536x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x1x1x1536x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x1x1x768x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x118x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x118x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x118x1x1x3x1x80x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x118x1x1x3x1x80x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1190x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1190x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1190x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1190x1x1x3x1x80x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1192x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1192x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1192x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1192x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1194x1x1x1x1x1536x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1194x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1194x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1194x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1194x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1194x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1194x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1194x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1194x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1194x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1194x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1194x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1194x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1198x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1198x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1198x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1198x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1199x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1199x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1199x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1199x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x119x1x1x1x1x1536x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x1x1x1536x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x1x1x768x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x119x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x119x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x119x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1201x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1201x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1201x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1201x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1202x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1202x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1202x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1202x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1206x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1206x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1206x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1206x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1207x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1207x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1207x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1207x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1209x1x1x1x1x1536x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1209x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1209x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1209x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1209x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1209x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1209x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1209x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1209x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x120x1x1x1x1x1536x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x1536x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x1536x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x1536x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x768x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x1x1x768x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x120x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x120x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x120x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x120x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x120x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x120x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1210x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1210x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1210x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1210x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1211x1x1x1x1x1536x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1211x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1211x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1211x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1211x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1211x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1211x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1211x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1211x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1211x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1211x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1211x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1211x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1216x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1216x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1216x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1216x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1218x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1218x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1218x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1218x1x1x3x1x80x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x121x1x1x1x1x1536x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x1x1x1536x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x1x1x768x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x121x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x121x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x121x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x121x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x121x1x1x3x1x80x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x121x1x1x3x1x80x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1221x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1221x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1221x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1225x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1225x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1225x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1225x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1227x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1227x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1227x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1227x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x122x1x1x1x1x1536x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x122x1x1x1x1x1536x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x122x1x1x1x1x768x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x122x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x122x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x122x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1232x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1232x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1232x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1232x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1234x1x1x1x1x1536x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x1234x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1234x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1234x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1234x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1234x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1234x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1234x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1234x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1234x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1234x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1234x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1234x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1236x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1236x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1236x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1236x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1238x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1238x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1238x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1238x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x123x1x1x1x1x1536x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x123x1x1x1x1x768x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x123x1x1x1x1x768x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x123x1x1x1x1x768x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x123x1x1x3x1x768x203x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x123x1x1x3x1x768x203x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x123x1x1x3x1x768x203x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x123x1x1x3x1x768x203x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x123x1x1x3x1x768x203x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x123x1x1x3x1x768x203x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1241x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1241x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1241x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1241x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1244x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1244x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1244x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1244x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1246x1x1x1x1x1536x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x1246x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1246x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1246x1x1x1x1x768x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1246x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1246x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1246x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1246x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1246x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1249x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1249x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1249x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1249x1x1x3x1x80x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x124x1x1x1x1x1536x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x124x1x1x1x1x768x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x124x1x1x1x1x768x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x124x1x1x1x1x768x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x124x1x1x3x1x768x201x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x124x1x1x3x1x768x201x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x124x1x1x3x1x768x201x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x124x1x1x3x1x768x201x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x124x1x1x3x1x768x201x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1254x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1254x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1254x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1254x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1256x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1256x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1256x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1256x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1259x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1259x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1259x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1259x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x125x1x1x1x1x1536x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x125x1x1x1x1x768x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x125x1x1x1x1x768x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x125x1x1x1x1x768x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x125x1x1x3x1x768x200x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x125x1x1x3x1x768x200x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x125x1x1x3x1x768x200x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x125x1x1x3x1x768x200x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x125x1x1x3x1x768x200x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x125x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x125x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x125x1x1x3x1x80x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x125x1x1x3x1x80x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1260x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1260x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1260x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1260x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1264x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1264x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1264x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1264x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x126x1x1x1x1x1536x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x1x1x1536x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x1x1x768x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x126x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x126x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x126x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x126x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x126x1x1x3x1x80x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x126x1x1x3x1x80x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1271x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1271x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1271x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1271x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1271x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1272x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1272x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1272x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1272x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1274x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1274x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1274x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1274x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1274x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1278x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1278x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1278x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1278x1x1x3x1x80x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x127x1x1x1x1x1536x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x1x1x1536x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x1x1x768x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x127x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x127x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x127x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1283x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1283x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1283x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1283x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1283x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1284x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x1x1x1536x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1284x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1285x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1285x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1285x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1285x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1286x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1286x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1286x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1286x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x128x1x1x1x1x1536x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x1x1x1536x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x1x1x768x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x128x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x128x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x128x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1293x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1293x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1293x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1293x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1296x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1296x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1296x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1296x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x1297x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1297x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1297x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1297x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1298x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1298x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1298x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1298x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1299x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1299x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1299x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1299x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x129x1x1x1x1x1536x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x1536x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x1536x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x1536x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x1x1x768x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x129x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x129x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x129x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x129x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x129x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x1x129x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1304x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1304x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1304x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1304x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1308x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1308x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1308x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1308x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x130x1x1x1x1x1536x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x1536x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x1536x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x1536x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x768x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x1x1x768x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x130x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x130x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x130x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x130x1x1x3x1x80x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x130x1x1x3x1x80x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1312x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1312x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1312x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1312x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1315x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1315x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1315x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1315x1x1x3x1x80x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1319x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1319x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1319x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1319x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x131x1x1x1x1x1536x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x1x1x1536x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x1x1x768x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x131x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x131x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x131x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x131x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1320x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1320x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1320x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1320x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1323x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1323x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1323x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1323x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1327x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1327x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1327x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1327x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x132x1x1x1x1x1536x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x1x1x1536x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x1x1x768x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x132x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x132x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x132x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x132x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1331x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1331x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1331x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1331x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1334x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1334x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1334x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1334x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x133x1x1x1x1x1536x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x1x1x1536x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x133x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x133x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x133x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x133x1x1x3x1x80x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x133x1x1x3x1x80x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1340x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1340x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1340x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1340x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1341x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1341x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1341x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1341x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1349x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1349x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1349x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1349x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x134x1x1x1x1x1536x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x1536x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x1536x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x1536x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x768x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x1x1x768x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x134x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x134x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x134x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x134x1x1x3x1x80x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x134x1x1x3x1x80x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1350x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1350x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1350x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1350x1x1x3x1x80x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1352x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1352x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1352x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1352x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1353x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1353x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1353x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1353x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1354x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1354x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1354x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1354x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x135x1x1x1x1x1536x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x135x1x1x1x1x1536x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x135x1x1x1x1x768x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x135x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x135x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x135x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1361x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1361x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1361x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1361x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1363x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1363x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1363x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1363x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1364x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1364x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1364x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1364x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1364x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1365x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1365x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x136x1x1x1x1x1536x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x1536x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x1536x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x1536x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x768x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x1x1x768x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x136x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x136x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x136x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x136x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x136x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1371x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1371x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1371x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1371x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x1372x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1372x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1372x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1372x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1373x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1373x1x1x1x1x1536x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1373x1x1x1x1x768x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1373x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1377x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1377x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1377x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1377x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1379x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1379x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1379x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1379x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x137x1x1x1x1x1536x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x1x1x1536x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x1x1x768x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x137x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x137x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x137x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x137x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x137x1x1x3x1x80x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x137x1x1x3x1x80x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1384x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1384x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1384x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1384x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1385x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1385x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1385x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1385x1x1x3x1x80x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x138x1x1x1x1x1536x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x1x1x1536x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x1x1x768x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x138x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x138x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x138x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x138x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1394x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1394x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1394x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1394x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1399x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1399x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1399x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1399x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x139x1x1x1x1x1536x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x1536x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x1536x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x1536x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x1x1x768x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x139x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x139x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x139x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x139x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x139x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1400x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1400x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1400x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1400x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x1408x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1408x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1408x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1408x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1409x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1409x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1409x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1409x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x140x1x1x1x1x1536x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x1536x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x140x1x1x1x1x1536x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x1536x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x768x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x1x1x768x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x140x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x140x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x140x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x140x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x140x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x140x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x140x1x1x3x1x80x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x140x1x1x3x1x80x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1413x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1413x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1413x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1413x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1417x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1417x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1417x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1417x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1419x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1419x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1419x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1419x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x141x1x1x1x1x1536x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x1x1x1536x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x141x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x141x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x141x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x141x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1422x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1422x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1422x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1422x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1426x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1426x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1426x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1426x1x1x3x1x80x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x142x1x1x1x1x1536x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x1x1x1536x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x1x1x768x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x142x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x142x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x142x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x142x1x1x3x1x80x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x142x1x1x3x1x80x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1431x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1431x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1431x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1431x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1432x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1432x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1432x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1432x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1433x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1433x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1433x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1433x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x143x1x1x1x1x1536x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x1x1x1536x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x1x1x768x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x143x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x143x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x143x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x143x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x143x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1440x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1440x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1440x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1440x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1443x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1443x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1443x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1443x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1444x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1444x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1444x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1444x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x144x1x1x1x1x1536x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x1x1x1536x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x1x1x768x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x144x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x144x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1451x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1451x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1451x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1451x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1452x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1452x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1452x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1452x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1454x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1454x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1454x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1454x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1456x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1456x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1456x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1456x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x145x1x1x1x1x1536x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x1x1x1536x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x1x1x768x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x145x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x145x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x145x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1463x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1463x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1463x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1463x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1468x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1468x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1468x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1468x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x146x1x1x1x1x1536x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x1x1x1536x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x146x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x146x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x146x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x146x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1470x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1470x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1470x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1470x1x1x3x1x80x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1473x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1473x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1473x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1475x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1475x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1475x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1479x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1479x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1479x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x147x1x1x1x1x1536x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x1x1x1536x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x1x1x768x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x147x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x147x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x147x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x147x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1487x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1487x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1487x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1488x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1488x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1488x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1488x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1489x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1489x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x148x1x1x1x1x1536x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x1536x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x1536x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x1536x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x768x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x1x1x768x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x148x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x148x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,153[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x148x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x148x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x148x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x148x1x1x3x1x80x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x148x1x1x3x1x80x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1496x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1496x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1496x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1496x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1497x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1497x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1499x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1499x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x149x1x1x1x1x1536x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x149x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x149x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x149x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x149x1x1x3x1x80x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x149x1x1x3x1x80x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1500x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x1x1x768x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x1500x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1500x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1500x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1500x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1502x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1502x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1502x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1502x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1507x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1507x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1507x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1507x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1509x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1509x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1509x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1509x1x1x3x1x80x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x150x1x1x1x1x1536x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x1x1x1536x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x1x1x768x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x1x1x768x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x1x1x768x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x1x1x768x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x150x1x1x3x1x768x166x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x166x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x3x1x768x166x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x150x1x1x3x1x768x166x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x166x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x150x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x150x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x150x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x150x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x150x1x1x3x1x80x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x150x1x1x3x1x80x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1516x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1516x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1516x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1516x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1521x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1521x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1521x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1521x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1523x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1523x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1523x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1523x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1527x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1527x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1527x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1527x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x152x1x1x1x1x1536x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x1x1x1536x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x1x1x768x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x152x1x1x1x1x768x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x1x1x768x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x152x1x1x1x1x768x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x152x1x1x1x1x768x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x1x1x768x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x152x1x1x3x1x768x164x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x152x1x1x3x1x768x164x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x3x1x768x164x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x152x1x1x3x1x768x164x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x152x1x1x3x1x768x164x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x152x1x1x3x1x768x165x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x152x1x1x3x1x768x165x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x152x1x1x3x1x768x165x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x152x1x1x3x1x768x165x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x152x1x1x3x1x768x165x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1533x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1533x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1533x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1533x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1535x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1535x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1535x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1535x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1539x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1539x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1539x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1539x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x153x1x1x1x1x1536x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x153x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x153x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x153x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x153x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x153x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x153x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x153x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x153x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1543x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1543x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1543x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1543x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1548x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1548x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1548x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1548x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x154x1x1x1x1x1536x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x154x1x1x1x1x768x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x154x1x1x1x1x768x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x154x1x1x1x1x768x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x154x1x1x3x1x768x162x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x154x1x1x3x1x768x162x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x154x1x1x3x1x768x162x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x154x1x1x3x1x768x162x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x154x1x1x3x1x768x162x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x154x1x1x3x1x768x324x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x154x1x1x3x1x80x324x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1551x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1551x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1551x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1551x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1552x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1552x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1552x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1552x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1555x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1555x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1555x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1555x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x155x1x1x1x1x1536x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x155x1x1x1x1x768x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x155x1x1x1x1x768x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x155x1x1x1x1x768x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x155x1x1x3x1x768x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x155x1x1x3x1x768x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x155x1x1x3x1x768x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x155x1x1x3x1x768x161x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x155x1x1x3x1x768x161x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x155x1x1x3x1x768x322x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x155x1x1x3x1x80x322x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1562x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1562x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1562x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1562x1x1x3x1x80x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1569x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1569x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1569x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1569x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x156x1x1x1x1x1536x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x156x1x1x1x1x768x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x156x1x1x1x1x768x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x156x1x1x1x1x768x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x156x1x1x3x1x768x160x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x156x1x1x3x1x768x160x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x156x1x1x3x1x768x160x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x156x1x1x3x1x768x160x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x156x1x1x3x1x768x160x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1570x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1570x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1570x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1570x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1573x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1573x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1573x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1573x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x157x1x1x1x1x1536x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x1x1x1536x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x1x1x768x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x157x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x157x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1586x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1586x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1586x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1586x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1587x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1587x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1587x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1587x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x158x1x1x1x1x1536x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x1x1x1536x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x1x1x768x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x158x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x158x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x158x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1594x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1594x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1594x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1594x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x159x1x1x1x1x1536x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x1x1x1536x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x1x1x768x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x159x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x159x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x159x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x159x1x1x3x1x80x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x159x1x1x3x1x80x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1603x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1603x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1603x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1603x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1606x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1606x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1606x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1606x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1607x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1607x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1607x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1607x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1608x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1608x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1608x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1608x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x160x1x1x1x1x1536x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x1x1x1536x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x1x1x768x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x160x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x160x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x160x1x1x3x1x80x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x160x1x1x3x1x80x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1610x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1610x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1610x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1610x1x1x3x1x80x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:175;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x161x1x1x1x1x1536x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x1x1x1536x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x1x1x768x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x161x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x161x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x161x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1625x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1625x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1625x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1625x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1626x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1626x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1626x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1626x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1628x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1628x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1628x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1628x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1629x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1629x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1629x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1629x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x162x1x1x1x1x1536x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x1x1x1536x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x1x1x768x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x162x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x162x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x162x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x162x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1636x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1636x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1636x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1636x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x163x1x1x1x1x1536x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x1x1x1536x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x1x1x768x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x163x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x163x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1646x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1646x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1646x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1646x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1647x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1647x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1647x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1647x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x164x1x1x1x1x1536x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x1x1x1536x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x1x1x768x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x164x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x164x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x164x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x164x1x1x3x1x80x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x164x1x1x3x1x80x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1651x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1651x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1651x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1651x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1654x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1654x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1654x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1654x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x165x1x1x1x1x1536x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x1x1x1536x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x165x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x165x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x165x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x165x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1660x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1660x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1660x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1660x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1662x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1662x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1662x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1662x1x1x3x1x80x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x166x1x1x1x1x1536x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x1536x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x166x1x1x1x1x1536x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x1536x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x768x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x166x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x166x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x166x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x166x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x166x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x166x1x1x3x1x80x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x166x1x1x3x1x80x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1675x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1675x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1675x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1675x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1676x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1676x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1676x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1676x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1679x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1679x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1679x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1679x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x167x1x1x1x1x1536x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x167x1x1x1x1x1536x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x167x1x1x1x1x768x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x167x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x167x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1680x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1680x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1680x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1680x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x168x1x1x1x1x1536x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x1x1x1536x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x1x1x768x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x168x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x168x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x168x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1698x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1698x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1698x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1698x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x169x1x1x1x1x1536x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x1x1x1536x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x169x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x169x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x169x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x169x1x1x3x1x80x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x169x1x1x3x1x80x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1703x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1703x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1703x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1703x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1708x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1708x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1708x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1708x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x170x1x1x1x1x1536x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x1x1x1536x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x1x1x768x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x170x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x170x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x170x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x170x1x1x3x1x80x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x170x1x1x3x1x80x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x171x1x1x1x1x1536x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x1x1x1536x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x1x1x768x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x171x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x171x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x171x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x171x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1722x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1722x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1722x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1722x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1724x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1724x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1724x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1724x1x1x3x1x80x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1728x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1728x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1728x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1728x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x172x1x1x1x1x1536x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x1x1x1536x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x1x1x768x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x172x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x172x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x172x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x172x1x1x3x1x80x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x172x1x1x3x1x80x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1733x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1733x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1733x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1733x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1734x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1734x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1734x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1734x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x173x1x1x1x1x1536x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x1x1x1536x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x1x1x768x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x173x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x173x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x173x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1748x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1748x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1748x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1748x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x174x1x1x1x1x1536x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x1x1x1536x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x174x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x174x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x174x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x174x1x1x3x1x80x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x174x1x1x3x1x80x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1759x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1759x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1759x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1759x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x175x1x1x1x1x1536x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x1536x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x1536x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x1536x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x1x1x768x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x175x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x175x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x175x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1760x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1760x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1760x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1760x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x176x1x1x1x1x1536x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x1x1x1536x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x1x1x768x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x176x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x176x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x176x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x176x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x176x1x1x3x1x80x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x176x1x1x3x1x80x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1770x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1770x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1770x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1770x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x177x1x1x1x1x1536x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x177x1x1x1x1x1536x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x177x1x1x1x1x768x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x177x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x177x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x177x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x177x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1782x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1782x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1782x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1782x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1784x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1784x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1784x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1784x1x1x3x1x80x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:185;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1786x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1786x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1786x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1786x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x178x1x1x1x1x1536x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x1x1x1536x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x178x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x178x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x178x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x178x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x178x1x1x3x1x80x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x178x1x1x3x1x80x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1791x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1791x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1791x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1791x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x179x1x1x1x1x1536x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x1536x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x1536x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x1536x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x768x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x1x1x768x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x179x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x179x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x179x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x179x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1806x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1806x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1806x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1806x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x180x1x1x1x1x1536x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x180x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x180x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x180x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x180x1x1x3x1x80x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x180x1x1x3x1x80x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x181x1x1x1x1x1536x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x1x1x1536x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x1x1x768x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x181x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x181x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x181x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x181x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x181x1x1x3x1x80x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x181x1x1x3x1x80x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1821x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1821x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1821x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1821x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1824x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1824x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1824x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1824x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x182x1x1x1x1x1536x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x182x1x1x1x1x768x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x182x1x1x1x1x768x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x182x1x1x1x1x768x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x182x1x1x3x1x768x137x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x182x1x1x3x1x768x137x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x182x1x1x3x1x768x137x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x182x1x1x3x1x768x137x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x182x1x1x3x1x768x137x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x182x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x182x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x182x1x1x3x1x80x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x182x1x1x3x1x80x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1833x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1833x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1833x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1833x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x183x1x1x1x1x1536x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x183x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x183x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x183x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x183x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x183x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x183x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x183x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x183x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1840x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1840x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1840x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1840x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1848x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1848x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1848x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1848x1x1x3x1x80x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x184x1x1x1x1x1536x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x184x1x1x1x1x1536x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x184x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x1x1x768x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x184x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x184x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x184x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x184x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x184x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x184x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x184x1x1x3x1x80x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x184x1x1x3x1x80x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1852x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1852x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1852x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1852x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x185x1x1x1x1x1536x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x185x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x185x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x185x1x1x1x1x768x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x185x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x185x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x185x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x185x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x185x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1869x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1869x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1869x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1869x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x186x1x1x1x1x1536x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x186x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x186x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x186x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x186x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x186x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x186x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x186x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x186x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x186x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x186x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x186x1x1x3x1x80x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x186x1x1x3x1x80x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1870x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1870x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1870x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1870x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:164;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x187x1x1x1x1x1536x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x1x1x1536x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x187x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x1x1x768x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x187x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x187x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x187x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x187x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x187x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x187x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1881x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1881x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1881x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1881x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1883x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1883x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1883x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1883x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x188x1x1x1x1x1536x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x1x1x1536x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x188x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x1x1x768x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x188x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x188x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x188x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x188x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x188x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x188x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x188x1x1x3x1x80x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x188x1x1x3x1x80x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x189x1x1x1x1x1536x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x189x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x189x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x189x1x1x1x1x768x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x189x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x189x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x189x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x189x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x189x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1902x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1902x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1902x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1902x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x190x1x1x1x1x1536x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x190x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x190x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x190x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x190x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x190x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x190x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x190x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x190x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x190x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x190x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x190x1x1x3x1x80x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x190x1x1x3x1x80x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1916x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1916x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1916x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1916x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1918x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1918x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1918x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1918x1x1x3x1x80x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x191x1x1x1x1x1536x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x1x1x1536x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x191x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x1x1x768x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x191x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x191x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x191x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x191x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x191x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x191x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1928x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1928x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1928x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1928x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x192x1x1x1x1x1536x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x192x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x192x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x192x1x1x1x1x768x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x192x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x192x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x192x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x192x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x192x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x192x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x192x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x192x1x1x3x1x80x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x192x1x1x3x1x80x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x193x1x1x1x1x1536x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x193x1x1x1x1x768x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x193x1x1x1x1x768x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x193x1x1x1x1x768x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x193x1x1x3x1x768x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x193x1x1x3x1x768x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x193x1x1x3x1x768x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x193x1x1x3x1x768x129x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x193x1x1x3x1x768x129x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x1942x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1942x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1942x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1942x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x194x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x194x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x194x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x194x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x194x1x1x3x1x80x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x194x1x1x3x1x80x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1957x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1957x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1957x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1957x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x195x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x1x1x1536x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x1x1x768x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x195x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x195x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x195x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x1960x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1960x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1960x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1960x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x196x1x1x1x1x1536x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x1x1x1536x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x196x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x196x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x196x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x196x1x1x3x1x80x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x196x1x1x3x1x80x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1979x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1979x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x197x1x1x1x1x1536x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x1x1x1536x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x197x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x197x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x197x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x1981x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1981x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1981x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1981x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x198x1x1x1x1x1536x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x1x1x1536x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x1x1x768x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x198x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x198x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x198x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x198x1x1x3x1x80x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x198x1x1x3x1x80x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1993x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1993x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1993x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1993x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x1997x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1997x1x1x3x1x80x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x199x1x1x1x1x1536x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x1x1x1536x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x199x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x199x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x199x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x199x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x3x1x768x251x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x199x1x1x3x1x80x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x199x1x1x3x1x80x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x1x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x1x1x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x1x1x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x1x1x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x1x2008x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2008x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2008x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2008x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x200x1x1x1x1x1536x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x1x1x1536x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x1x1x768x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x200x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x200x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x200x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x3x1x768x250x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x200x1x1x3x1x80x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x200x1x1x3x1x80x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2017x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2017x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2017x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2017x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x201x1x1x1x1x1536x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x201x1x1x1x1x1536x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x201x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x201x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x201x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x201x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2025x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2025x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2025x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2025x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x202x1x1x1x1x1536x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x1536x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x1536x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x1536x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x1x1x768x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x202x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x202x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x202x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x202x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x202x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x768x247x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x202x1x1x3x1x80x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x202x1x1x3x1x80x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x203x1x1x1x1x1536x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x1x1x1536x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x1x1x768x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x203x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x203x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x203x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x203x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x204x1x1x1x1x1536x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x1x1x1536x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x1x1x768x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x204x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x204x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x2051x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2051x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2051x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2051x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2053x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2053x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2053x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2053x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2056x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2056x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2056x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2056x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2057x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2057x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2057x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2057x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x205x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x205x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x205x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x205x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x205x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x3x1x768x243x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x205x1x1x3x1x80x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x205x1x1x3x1x80x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x206x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x206x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x206x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x206x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x3x1x768x242x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x206x1x1x3x1x80x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x206x1x1x3x1x80x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2074x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2074x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2074x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2074x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x207x1x1x1x1x1536x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x1536x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x1536x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x1x1x768x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x207x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x207x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x207x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x207x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x768x241x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x207x1x1x3x1x80x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x207x1x1x3x1x80x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2082x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2082x1x1x3x1x768x24x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2082x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2082x1x1x3x1x80x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x208x1x1x1x1x1536x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x1x1x1536x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x1x1x768x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x208x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x208x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x3x1x768x240x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x208x1x1x3x1x80x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x208x1x1x3x1x80x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2098x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2098x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2098x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2098x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x209x1x1x1x1x1536x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x1x1x1536x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x209x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x209x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x209x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2102x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2102x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2102x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2102x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2105x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2105x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2105x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2105x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x210x1x1x1x1x1536x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x1x1x1536x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x1x1x768x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x210x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x210x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x210x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x3x1x768x238x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x210x1x1x3x1x80x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x210x1x1x3x1x80x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x211x1x1x1x1x1536x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x1x1x1536x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x211x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x211x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x211x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2127x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2127x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2127x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2127x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x212x1x1x1x1x1536x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x1x1x1536x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x1x1x768x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x212x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x212x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x212x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x212x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x3x1x768x235x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x212x1x1x3x1x80x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x212x1x1x3x1x80x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2134x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2134x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2134x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2134x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x213x1x1x1x1x1536x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x1x1x1536x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x213x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x213x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x213x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2146x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2146x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2146x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2146x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x214x1x1x1x1x1536x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x1536x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x214x1x1x1x1x1536x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x1536x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x1x1x768x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x214x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x214x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x214x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x214x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x214x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x768x233x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x214x1x1x3x1x80x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x214x1x1x3x1x80x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2152x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2152x1x1x3x1x768x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2152x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2152x1x1x3x1x80x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x215x1x1x1x1x1536x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x1x1x1536x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x1x1x768x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x215x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x215x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x215x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x216x1x1x1x1x1536x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x1x1x1536x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x216x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x216x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x216x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x3x1x768x231x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x216x1x1x3x1x80x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x216x1x1x3x1x80x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x217x1x1x1x1x1536x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x1x1x1536x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x1x1x768x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x217x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x217x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x217x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x217x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x3x1x768x230x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x217x1x1x3x1x80x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x217x1x1x3x1x80x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2182x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2182x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2182x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2182x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x218x1x1x1x1x1536x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x1x1x1536x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x218x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x218x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x218x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x218x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x3x1x768x229x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x218x1x1x3x1x80x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x218x1x1x3x1x80x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2190x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2190x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2190x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2190x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x219x1x1x1x1x1536x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x1x1x1536x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x219x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x219x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x219x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x219x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x3x1x768x228x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x219x1x1x3x1x80x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x219x1x1x3x1x80x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2205x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2205x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2205x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2205x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x220x1x1x1x1x1536x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x1x1x1536x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x220x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x220x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x220x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x220x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x3x1x768x227x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x220x1x1x3x1x80x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x220x1x1x3x1x80x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x221x1x1x1x1x1536x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x221x1x1x1x1x1536x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x221x1x1x1x1x768x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x221x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x221x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x221x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x222x1x1x1x1x1536x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x1x1x1536x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x222x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x222x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x3x1x768x225x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x222x1x1x3x1x80x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x222x1x1x3x1x80x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2233x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2233x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2233x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2233x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x223x1x1x1x1x1536x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x1x1x1536x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x1x1x768x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x223x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x223x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x224x1x1x1x1x1536x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x1x1x1536x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x224x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x224x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x224x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x3x1x768x223x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x224x1x1x3x1x80x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x224x1x1x3x1x80x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2251x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2251x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2251x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2251x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2257x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2257x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2257x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2257x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x225x1x1x1x1x1536x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x225x1x1x1x1x1536x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x225x1x1x1x1x768x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x225x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x225x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x225x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x2260x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2260x1x1x3x1x768x22x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2260x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2260x1x1x3x1x80x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x226x1x1x1x1x1536x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x226x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x226x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x226x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x226x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x226x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x226x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x226x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x226x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x226x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x226x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x226x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x226x1x1x3x1x768x221x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x226x1x1x3x1x80x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x226x1x1x3x1x80x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2278x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2278x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2278x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2278x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x227x1x1x1x1x1536x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x227x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x227x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x227x1x1x1x1x768x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x227x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x227x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x227x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x227x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x227x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2282x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2282x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2282x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2282x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x228x1x1x1x1x1536x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x228x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x228x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x228x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x228x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x228x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x228x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x228x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x228x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x228x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x228x1x1x3x1x768x219x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x228x1x1x3x1x80x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x228x1x1x3x1x80x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x229x1x1x1x1x1536x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x229x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x229x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x229x1x1x1x1x768x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x229x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x229x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x229x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x229x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x229x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x229x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x229x1x1x3x1x768x218x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x229x1x1x3x1x80x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x229x1x1x3x1x80x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x230x1x1x1x1x1536x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x230x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x230x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x230x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x230x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x230x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x230x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x230x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x230x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x230x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x230x1x1x3x1x768x217x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x230x1x1x3x1x80x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x230x1x1x3x1x80x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2315x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2315x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2315x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2315x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2318x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2318x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2318x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2318x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x231x1x1x1x1x1536x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x231x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x231x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x231x1x1x1x1x768x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x231x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x231x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x231x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x231x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x231x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x232x1x1x1x1x1536x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x232x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x232x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x232x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x232x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x232x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x232x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x232x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x232x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x232x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x232x1x1x3x1x768x215x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x232x1x1x3x1x80x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x232x1x1x3x1x80x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x233x1x1x1x1x1536x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x233x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x233x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x233x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x233x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x233x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x233x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x233x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x233x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x233x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x233x1x1x3x1x768x214x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x233x1x1x3x1x80x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x233x1x1x3x1x80x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2346x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2346x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2346x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2346x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x234x1x1x1x1x1536x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x1x1x1536x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x234x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x234x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x1x1x768x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x234x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x234x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x234x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x234x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x234x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x234x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x3x1x768x213x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x234x1x1x3x1x80x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x234x1x1x3x1x80x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x235x1x1x1x1x1536x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x235x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x235x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x235x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x235x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x235x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x235x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x235x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x235x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x236x1x1x1x1x1536x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x1x1x1536x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x236x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x1x1x768x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x236x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x236x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x236x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x236x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x236x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x236x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x3x1x768x211x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x236x1x1x3x1x80x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x236x1x1x3x1x80x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2372x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2372x1x1x3x1x768x21x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2372x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2372x1x1x3x1x80x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x237x1x1x1x1x1536x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x237x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x237x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x237x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x237x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x237x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x237x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x237x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x237x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x2388x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2388x1x1x3x1x80x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x238x1x1x1x1x1536x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x238x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x238x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x238x1x1x1x1x768x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x238x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x238x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x238x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x238x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x238x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x238x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x238x1x1x3x1x768x210x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x238x1x1x3x1x80x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x238x1x1x3x1x80x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x239x1x1x1x1x1536x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x239x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x239x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x239x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x239x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x239x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x239x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x239x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x239x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x239x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x239x1x1x3x1x768x209x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x239x1x1x3x1x80x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x239x1x1x3x1x80x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x240x1x1x1x1x1536x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x240x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x240x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x240x1x1x1x1x768x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x240x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x240x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x240x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x240x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x240x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x240x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x240x1x1x3x1x768x208x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x240x1x1x3x1x80x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x240x1x1x3x1x80x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2417x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2417x1x1x3x1x80x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x241x1x1x1x1x1536x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x241x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x241x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x241x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x241x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x241x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x241x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x241x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x241x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2422x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2422x1x1x3x1x80x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x242x1x1x1x1x1536x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x242x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x242x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x242x1x1x1x1x768x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x242x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x242x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x242x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x242x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x242x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x242x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x242x1x1x3x1x768x206x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x242x1x1x3x1x80x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x242x1x1x3x1x80x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x243x1x1x1x1x1536x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x243x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x243x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x243x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x243x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x243x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x243x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x243x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x243x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x244x1x1x1x1x1536x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x244x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x244x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x244x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x244x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x244x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x244x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x244x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x244x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x244x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x244x1x1x3x1x768x204x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x244x1x1x3x1x80x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x244x1x1x3x1x80x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x245x1x1x1x1x1536x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x245x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x245x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x245x1x1x1x1x768x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x245x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x245x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x245x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x245x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x245x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2467x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2467x1x1x3x1x80x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x246x1x1x1x1x1536x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x246x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x246x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x246x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x246x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x246x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x246x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x246x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x246x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x246x1x1x3x1x768x203x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x246x1x1x3x1x80x203x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x247x1x1x1x1x1536x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x247x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x247x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x247x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x247x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x247x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x247x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x247x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x247x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x248x1x1x1x1x1536x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x1x1x1536x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x248x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x248x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x248x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x248x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x248x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x248x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x248x1x1x3x1x768x201x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x248x1x1x3x1x80x201x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2492x1x1x3x1x768x20x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2492x1x1x3x1x80x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x249x1x1x1x1x1536x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x249x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x249x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x249x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x249x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x249x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x249x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x249x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x249x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x250x1x1x1x1x1536x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x250x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x250x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x250x1x1x1x1x768x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x250x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x250x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x250x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x250x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x250x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x250x1x1x3x1x768x200x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x250x1x1x3x1x80x200x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x251x1x1x1x1x1536x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x251x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x251x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x251x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x251x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x251x1x1x3x1x768x199x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x251x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x251x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x251x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x251x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x251x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x251x1x1x3x1x80x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x251x1x1x3x1x80x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x252x1x1x1x1x1536x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x252x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x252x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x252x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x252x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x252x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x252x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x252x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x252x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x253x1x1x1x1x1536x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x1x1x1536x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x253x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x253x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x253x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x1x1x768x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x253x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x253x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x253x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x253x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x253x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x253x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x253x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x253x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x253x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2542x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2542x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2542x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2542x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2548x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2548x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2548x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2548x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x254x1x1x1x1x1536x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x254x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x254x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x254x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x254x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x254x1x1x3x1x768x196x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x254x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x254x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x254x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x254x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x254x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x254x1x1x3x1x80x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x254x1x1x3x1x80x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x255x1x1x1x1x1536x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x255x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x255x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x255x1x1x1x1x768x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x255x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x255x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x255x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x255x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x255x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x2566x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2566x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2566x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2566x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2568x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2568x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2568x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2568x1x1x3x1x80x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x256x1x1x1x1x1536x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x256x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x256x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x256x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x256x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x256x1x1x3x1x768x195x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x256x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x256x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x256x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x256x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x256x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x256x1x1x3x1x80x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x256x1x1x3x1x80x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x257x1x1x1x1x1536x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x257x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x257x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x257x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x257x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x257x1x1x3x1x768x194x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x257x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x257x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x257x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x257x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x257x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x257x1x1x3x1x80x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x257x1x1x3x1x80x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x258x1x1x1x1x1536x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x1x1x1536x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x258x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x258x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x258x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x1x1x768x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x258x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x258x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x258x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x258x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x258x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x258x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x258x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x258x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x258x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x258x1x1x3x1x80x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x258x1x1x3x1x80x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x259x1x1x1x1x1536x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x259x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x259x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x259x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x259x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x259x1x1x3x1x768x193x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x259x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x259x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x259x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x259x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x259x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x259x1x1x3x1x80x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x259x1x1x3x1x80x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x260x1x1x1x1x1536x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x260x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x260x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x260x1x1x1x1x768x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x260x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x260x1x1x3x1x768x192x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x260x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x260x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x260x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x260x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x260x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x260x1x1x3x1x80x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x260x1x1x3x1x80x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x261x1x1x1x1x1536x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x261x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x261x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x261x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x261x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x261x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x261x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x261x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x261x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x262x1x1x1x1x1536x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x262x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x262x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x262x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x262x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x262x1x1x3x1x768x190x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x262x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x262x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x262x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x262x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x262x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x262x1x1x3x1x80x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x262x1x1x3x1x80x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x263x1x1x1x1x1536x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x263x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x263x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x263x1x1x1x1x768x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x263x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x263x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x263x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x263x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x263x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x264x1x1x1x1x1536x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x264x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x264x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x264x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x264x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x264x1x1x3x1x768x189x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x264x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x264x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x264x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x264x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x264x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x264x1x1x3x1x80x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x264x1x1x3x1x80x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x265x1x1x1x1x1536x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x265x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x265x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x265x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x265x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x265x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x265x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x265x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x265x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x266x1x1x1x1x1536x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x1x1x1536x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x266x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x266x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x266x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x1x1x768x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x266x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x266x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x266x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x266x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x266x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x266x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x266x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x266x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x266x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x266x1x1x3x1x80x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x266x1x1x3x1x80x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x267x1x1x1x1x1536x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x267x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x267x1x1x3x1x768x187x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x267x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x267x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x267x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x267x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x267x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x267x1x1x3x1x80x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x267x1x1x3x1x80x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x268x1x1x1x1x1536x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x268x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x268x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x268x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x268x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x268x1x1x3x1x768x186x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x268x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x268x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x268x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x268x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x268x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x268x1x1x3x1x80x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x268x1x1x3x1x80x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x269x1x1x1x1x1536x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x1x1x1536x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x269x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x269x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x269x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x269x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x269x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x269x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x269x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x269x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x269x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x269x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x269x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x269x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x269x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x269x1x1x3x1x80x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x269x1x1x3x1x80x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x26x1x1x1x1x1536x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x1x1x1536x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x1x26x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x1x1x768x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x768x1x26x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x1x26x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x26x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x1x26x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x26x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x768x1x26x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x26x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,2,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x1x26x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x26x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x768x1x26x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,189[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x1x26x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x768x1x270x1x1x1x1x1536x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x270x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x270x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x270x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x270x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x270x1x1x3x1x768x185x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x270x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x270x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x270x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x270x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x270x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x270x1x1x3x1x80x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x270x1x1x3x1x80x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x271x1x1x1x1x1536x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x271x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x271x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x271x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x271x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x271x1x1x3x1x768x184x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x271x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x271x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x271x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x271x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x271x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x271x1x1x3x1x80x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x271x1x1x3x1x80x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2727x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2727x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2727x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2727x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2729x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2729x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2729x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2729x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:162;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x272x1x1x1x1x1536x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x1x1x1536x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x272x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x272x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x272x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x1x1x768x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x272x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x3x1x768x183x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x272x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x272x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x272x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x272x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x272x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x272x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x272x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x272x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x272x1x1x3x1x80x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x272x1x1x3x1x80x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x273x1x1x1x1x1536x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x273x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x273x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x273x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x273x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x273x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x273x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x273x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x273x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x2745x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2745x1x1x3x1x768x18x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2745x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2745x1x1x3x1x80x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x274x1x1x1x1x1536x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x274x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x274x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x274x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x274x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x274x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x274x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x274x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x274x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x274x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x274x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x274x1x1x3x1x80x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x274x1x1x3x1x80x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x275x1x1x1x1x1536x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x1x1x1536x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x275x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x275x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x275x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x275x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x1x1x768x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x275x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x275x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x275x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x275x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x275x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x275x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x275x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x275x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x275x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x275x1x1x3x1x80x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x275x1x1x3x1x80x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x276x1x1x1x1x1536x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x276x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x276x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x276x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x276x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x276x1x1x3x1x768x181x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x276x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x276x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x276x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x276x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x276x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x276x1x1x3x1x80x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x276x1x1x3x1x80x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x277x1x1x1x1x1536x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x277x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x277x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x277x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x277x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x277x1x1x3x1x768x180x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x277x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x277x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x277x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x277x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x277x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x277x1x1x3x1x80x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x277x1x1x3x1x80x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x278x1x1x1x1x1536x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x1x1x1536x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x278x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x278x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x278x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x1x1x768x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x278x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x278x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x278x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x278x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x278x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x278x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x278x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x278x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x278x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x278x1x1x3x1x80x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x278x1x1x3x1x80x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x279x1x1x1x1x1536x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x279x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x279x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x279x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x279x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x279x1x1x3x1x768x179x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x279x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x279x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x279x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x279x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x279x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x279x1x1x3x1x80x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x279x1x1x3x1x80x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x280x1x1x1x1x1536x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x280x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x280x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x280x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x280x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x280x1x1x3x1x768x178x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x280x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x280x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x280x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x280x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x280x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x280x1x1x3x1x80x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x280x1x1x3x1x80x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x281x1x1x1x1x1536x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x1x1x1536x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x281x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x281x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x281x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x1x1x768x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x281x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x281x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x281x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x281x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x281x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x281x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x281x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x281x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x281x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x282x1x1x1x1x1536x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x282x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x282x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x282x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x282x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x282x1x1x3x1x768x177x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x282x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x282x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x282x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x282x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x282x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x282x1x1x3x1x80x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x282x1x1x3x1x80x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x283x1x1x1x1x1536x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x283x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x283x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x283x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x283x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x283x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x283x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x283x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x283x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x283x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x283x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x283x1x1x3x1x80x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x283x1x1x3x1x80x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x284x1x1x1x1x1536x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x284x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x284x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x284x1x1x1x1x768x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x284x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x284x1x1x3x1x768x176x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x284x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x284x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x284x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x284x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x284x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x284x1x1x3x1x80x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x284x1x1x3x1x80x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x285x1x1x1x1x1536x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x285x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x285x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x285x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x285x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x285x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x285x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x285x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x285x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x286x1x1x1x1x1536x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x286x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x286x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x286x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x286x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x286x1x1x3x1x768x174x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x286x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x286x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x286x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x286x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x286x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x286x1x1x3x1x80x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x286x1x1x3x1x80x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x287x1x1x1x1x1536x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x287x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x287x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x287x1x1x1x1x768x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x287x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x287x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x287x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x287x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x287x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x288x1x1x1x1x1536x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x288x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x288x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x288x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x288x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x288x1x1x3x1x768x173x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x288x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x288x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x288x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x288x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x288x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x288x1x1x3x1x80x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x288x1x1x3x1x80x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x289x1x1x1x1x1536x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x289x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x289x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x289x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x289x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x289x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x289x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x289x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x289x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x290x1x1x1x1x1536x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x290x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x290x1x1x3x1x768x172x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x290x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x290x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x290x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x290x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x290x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x290x1x1x3x1x80x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x290x1x1x3x1x80x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x291x1x1x1x1x1536x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x1x1x1536x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x291x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x291x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x291x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x291x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x291x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x291x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x291x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x291x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x291x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x291x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x291x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x291x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x291x1x1x3x1x80x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x291x1x1x3x1x80x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x292x1x1x1x1x1536x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x292x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x292x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x292x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x292x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x292x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x292x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x292x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x292x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x292x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x292x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x292x1x1x3x1x80x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x292x1x1x3x1x80x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x293x1x1x1x1x1536x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x293x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x293x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x293x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x293x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x293x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x293x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x293x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x293x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x294x1x1x1x1x1536x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x294x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x294x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x294x1x1x1x1x768x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x294x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x294x1x1x3x1x768x170x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x294x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x294x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x294x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x294x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x294x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x294x1x1x3x1x80x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x294x1x1x3x1x80x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x295x1x1x1x1x1536x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x295x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x295x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x295x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x295x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x295x1x1x3x1x768x169x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x295x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x295x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x295x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x295x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x295x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x295x1x1x3x1x80x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x295x1x1x3x1x80x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x296x1x1x1x1x1536x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x296x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x296x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x296x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x296x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x296x1x1x3x1x768x168x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x296x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x296x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x296x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x296x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x296x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x296x1x1x3x1x80x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x296x1x1x3x1x80x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2978x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2978x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2978x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2978x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x297x1x1x1x1x1536x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x297x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x297x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x297x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x297x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x297x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x297x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x297x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x297x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x298x1x1x1x1x1536x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x298x1x1x1x1x1536x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x298x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x298x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x298x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x1x1x768x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x298x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x298x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x298x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x298x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x298x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x298x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x298x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x298x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x298x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x298x1x1x3x1x80x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x298x1x1x3x1x80x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2994x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2994x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2994x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2994x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2997x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2997x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x2997x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x2997x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x299x1x1x1x1x1536x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x299x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x299x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x299x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x299x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x299x1x1x3x1x768x167x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x299x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x299x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x299x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x299x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x299x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x299x1x1x3x1x80x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x299x1x1x3x1x80x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x3000x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x3000x1x1x3x1x768x16x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x3000x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x3000x1x1x3x1x80x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x300x1x1x1x1x1536x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x300x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x300x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x300x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x300x1x1x3x1x768x166x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x300x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x300x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x300x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x300x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x300x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x300x1x1x3x1x80x166x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x301x1x1x1x1x1536x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x301x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x301x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x301x1x1x1x1x768x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x301x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x301x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x301x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x301x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x301x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x302x1x1x1x1x1536x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x302x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x302x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x302x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x302x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x302x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x302x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x302x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x302x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x303x1x1x1x1x1536x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x303x1x1x3x1x768x165x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x303x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x303x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x303x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x303x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x303x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x303x1x1x3x1x80x165x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x304x1x1x1x1x1536x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x304x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x304x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x304x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x304x1x1x3x1x768x164x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x304x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x304x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x304x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x304x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x304x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x304x1x1x3x1x80x164x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x305x1x1x1x1x1536x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x305x1x1x1x1x1536x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x305x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x305x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x305x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x305x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x305x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x305x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x305x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x305x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x305x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x305x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x305x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x305x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x305x1x1x3x1x80x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x306x1x1x1x1x1536x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x306x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x306x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x306x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x306x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x306x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x306x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x306x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x306x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x306x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x306x1x1x3x1x80x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x307x1x1x1x1x1536x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x307x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x307x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x307x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x307x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x307x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x307x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x307x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x307x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x308x1x1x1x1x1536x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x308x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x308x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x308x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x308x1x1x3x1x768x162x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x308x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x308x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x308x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x308x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x308x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x308x1x1x3x1x80x162x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x309x1x1x1x1x1536x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x1x1x1536x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x309x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x309x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x309x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x1x1x768x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x309x1x1x3x1x768x161x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x309x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x309x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x309x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x309x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x309x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x309x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x309x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x309x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x309x1x1x3x1x80x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x310x1x1x1x1x1536x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x310x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x310x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x310x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x310x1x1x3x1x768x161x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x310x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x310x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x310x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x310x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x310x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x310x1x1x3x1x80x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x311x1x1x1x1x1536x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x311x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x311x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x311x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x311x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x311x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x311x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x311x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x311x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x312x1x1x1x1x1536x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x312x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x312x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x312x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x312x1x1x3x1x768x160x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x312x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x312x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x312x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x312x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x312x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x312x1x1x3x1x80x160x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x313x1x1x1x1x1536x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x1x1x1536x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x313x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x313x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x313x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x1x1x768x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x313x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x313x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x313x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x313x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x313x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x313x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x313x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x313x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x313x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x314x1x1x1x1x1536x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x314x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x314x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x314x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x314x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x314x1x1x3x1x768x159x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x314x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x314x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x314x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x314x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x314x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x314x1x1x3x1x80x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x314x1x1x3x1x80x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x315x1x1x1x1x1536x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x315x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x315x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x315x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x315x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x315x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x315x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x315x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x315x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x315x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x315x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x315x1x1x3x1x80x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x315x1x1x3x1x80x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x316x1x1x1x1x1536x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x316x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x316x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x316x1x1x1x1x768x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x316x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x316x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x316x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x316x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x316x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x316x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x316x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x316x1x1x3x1x80x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x316x1x1x3x1x80x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x317x1x1x1x1x1536x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x317x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x317x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x317x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x317x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x317x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x317x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x317x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x317x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x317x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x317x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x317x1x1x3x1x80x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x317x1x1x3x1x80x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x318x1x1x1x1x1536x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x318x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x318x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x318x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x318x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x318x1x1x3x1x768x157x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x318x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x318x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x318x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x318x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x318x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x318x1x1x3x1x80x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x318x1x1x3x1x80x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x319x1x1x1x1x1536x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x319x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x319x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x319x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x319x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x319x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x319x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x319x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x319x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x319x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x319x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x319x1x1x3x1x80x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x319x1x1x3x1x80x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x31x1x1x1x1x1536x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x1x1x1536x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x1x1x768x462x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x31x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x31x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x31x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x320x1x1x1x1x1536x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x320x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x320x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x320x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x320x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x320x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x320x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x320x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x320x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x320x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x320x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x320x1x1x3x1x80x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x320x1x1x3x1x80x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x321x1x1x1x1x1536x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x1x1x1536x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x321x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x321x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x321x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x1x1x768x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x321x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x321x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x321x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x321x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x321x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x321x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x321x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x321x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x321x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x322x1x1x1x1x1536x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x322x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x322x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x322x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x322x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x322x1x1x3x1x768x155x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x322x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x322x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x322x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x322x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x322x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x322x1x1x3x1x80x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x322x1x1x3x1x80x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x323x1x1x1x1x1536x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x323x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x323x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x323x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x323x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x323x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x323x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x323x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x323x1x1x3x1x80x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x323x1x1x3x1x80x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x324x1x1x1x1x1536x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x324x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x324x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x324x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x324x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x324x1x1x3x1x768x154x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x324x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x324x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x324x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x324x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x324x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x324x1x1x3x1x80x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x324x1x1x3x1x80x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x325x1x1x1x1x1536x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x1x1x1536x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x325x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x325x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x325x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x325x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x325x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x325x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x325x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x325x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x325x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x325x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x325x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x325x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x325x1x1x3x1x80x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x325x1x1x3x1x80x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x326x1x1x1x1x1536x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x326x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x326x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x326x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x326x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x326x1x1x3x1x768x153x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x326x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x326x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x326x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x326x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x326x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x326x1x1x3x1x80x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x326x1x1x3x1x80x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x327x1x1x1x1x1536x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x327x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x327x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x327x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x327x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x327x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x327x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x327x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x327x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x328x1x1x1x1x1536x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x328x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x328x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x328x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x328x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x328x1x1x3x1x768x152x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x328x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x328x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x328x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x328x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x328x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x328x1x1x3x1x80x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x328x1x1x3x1x80x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x329x1x1x1x1x1536x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x1x1x1536x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x329x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x329x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x329x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x1x1x768x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x329x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x329x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x329x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x329x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x329x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x329x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x329x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x329x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x329x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x330x1x1x1x1x1536x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x330x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x330x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x330x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x330x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x330x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x330x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x330x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x330x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x330x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x330x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x330x1x1x3x1x80x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x330x1x1x3x1x80x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x331x1x1x1x1x1536x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x331x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x331x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x331x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x331x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x331x1x1x3x1x768x151x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x331x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x331x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x331x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x331x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x331x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x331x1x1x3x1x80x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x331x1x1x3x1x80x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x332x1x1x1x1x1536x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x332x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x332x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x332x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x332x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x332x1x1x3x1x768x150x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x332x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x332x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x332x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x332x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x332x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x332x1x1x3x1x80x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x332x1x1x3x1x80x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x333x1x1x1x1x1536x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x333x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x333x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x333x1x1x1x1x768x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x333x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x333x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x333x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x333x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x333x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x334x1x1x1x1x1536x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x334x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x334x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x334x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x334x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x334x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x334x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x334x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x334x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x334x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x334x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x334x1x1x3x1x80x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x334x1x1x3x1x80x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x335x1x1x1x1x1536x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x335x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x335x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x335x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x335x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x335x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x335x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x335x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x335x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x336x1x1x1x1x1536x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x336x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x336x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x336x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x336x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x336x1x1x3x1x768x148x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x336x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x336x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x336x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x336x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x336x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x336x1x1x3x1x80x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x336x1x1x3x1x80x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x337x1x1x1x1x1536x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x337x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x337x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x337x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x337x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x337x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x337x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x337x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x337x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x338x1x1x1x1x1536x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x1x1x1536x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x338x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x338x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x338x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x338x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x338x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x338x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x338x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x338x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x338x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x338x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x338x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x338x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x339x1x1x1x1x1536x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x339x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x339x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x339x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x339x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x339x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x339x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x339x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x339x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x339x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x339x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x339x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x339x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x33x1x1x1x1x1536x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x33x1x1x1x1x768x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x33x1x1x1x1x768x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x33x1x1x1x1x768x517x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x33x1x1x3x1x768x517x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x1x33x1x1x3x1x768x517x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x33x1x1x3x1x768x517x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x33x1x1x3x1x768x517x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x768x1x33x1x1x3x1x768x517x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x340x1x1x1x1x1536x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x340x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x340x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x340x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x340x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x340x1x1x3x1x768x147x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x340x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x340x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x340x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x340x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x340x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x340x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x340x1x1x3x1x80x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x341x1x1x1x1x1536x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x341x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x341x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x341x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x341x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x341x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x341x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x341x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x341x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x341x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x341x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x341x1x1x3x1x80x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x341x1x1x3x1x80x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x342x1x1x1x1x1536x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x342x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x342x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x342x1x1x1x1x768x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x342x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x342x1x1x3x1x768x146x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x342x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x342x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x342x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x342x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x342x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x342x1x1x3x1x80x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x342x1x1x3x1x80x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x343x1x1x1x1x1536x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x343x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x343x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x343x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x343x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x343x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x343x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x343x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x343x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x343x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x343x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x343x1x1x3x1x80x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x343x1x1x3x1x80x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x344x1x1x1x1x1536x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x344x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x344x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x344x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x344x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x344x1x1x3x1x768x145x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x344x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x344x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x344x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x344x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x344x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x344x1x1x3x1x80x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x344x1x1x3x1x80x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x345x1x1x1x1x1536x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x345x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x345x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x345x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x345x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x345x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x345x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x345x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x345x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x345x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x345x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x345x1x1x3x1x80x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x345x1x1x3x1x80x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x346x1x1x1x1x1536x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x346x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x346x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x346x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x346x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x346x1x1x3x1x768x144x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x346x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x346x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x346x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x346x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x346x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x346x1x1x3x1x80x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x346x1x1x3x1x80x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x347x1x1x1x1x1536x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x347x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x347x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x347x1x1x1x1x768x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x347x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x347x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x347x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x347x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x347x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x348x1x1x1x1x1536x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x348x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x348x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x348x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x348x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x348x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x348x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x348x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x348x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x348x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x348x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x348x1x1x3x1x80x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x348x1x1x3x1x80x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x349x1x1x1x1x1536x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x349x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x349x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x349x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x349x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x349x1x1x3x1x768x143x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x349x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x349x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x349x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x349x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x349x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x349x1x1x3x1x80x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x349x1x1x3x1x80x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x350x1x1x1x1x1536x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x350x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x350x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x350x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x350x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x350x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x350x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x350x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x350x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x350x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x350x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x350x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x350x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x351x1x1x1x1x1536x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x351x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x351x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x351x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x351x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x351x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x351x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x351x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x351x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x351x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x351x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x351x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x351x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x352x1x1x1x1x1536x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x352x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x352x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x352x1x1x1x1x768x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x352x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x352x1x1x3x1x768x142x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x352x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x352x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x352x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x352x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x352x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x352x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x352x1x1x3x1x80x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x353x1x1x1x1x1536x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x353x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x353x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x353x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x353x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x353x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x353x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x353x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x353x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x354x1x1x1x1x1536x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x354x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x354x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x354x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x354x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x354x1x1x3x1x768x141x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x354x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x354x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x354x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x354x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x354x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x354x1x1x3x1x80x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x354x1x1x3x1x80x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x355x1x1x1x1x1536x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x355x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x355x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x355x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x355x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x355x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x355x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x355x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x355x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x355x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x355x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x355x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x355x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x356x1x1x1x1x1536x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x356x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x356x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x356x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x356x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x356x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x356x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x356x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x356x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x356x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x356x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x356x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x356x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x357x1x1x1x1x1536x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x357x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x357x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x357x1x1x1x1x768x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x357x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x357x1x1x3x1x768x140x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x357x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x357x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x357x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x357x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x357x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x357x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x357x1x1x3x1x80x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x358x1x1x1x1x1536x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x358x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x358x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x358x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x358x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x358x1x1x3x1x768x139x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x358x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x358x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x358x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x358x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x358x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x358x1x1x3x1x80x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x358x1x1x3x1x80x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x359x1x1x1x1x1536x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x359x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x359x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x359x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x359x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x359x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x359x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x359x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x359x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x360x1x1x1x1x1536x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x360x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x360x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x360x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x360x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x360x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x360x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x360x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x360x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x360x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x360x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x360x1x1x3x1x80x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x360x1x1x3x1x80x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x361x1x1x1x1x1536x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x361x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x361x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x361x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x361x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x361x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x361x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x361x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x361x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x362x1x1x1x1x1536x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x362x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x362x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x362x1x1x1x1x768x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x362x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x362x1x1x3x1x768x138x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x362x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x362x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x362x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x362x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x362x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x362x1x1x3x1x80x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x362x1x1x3x1x80x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x363x1x1x1x1x1536x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x363x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x363x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x363x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x363x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x363x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x363x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x363x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x363x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x364x1x1x1x1x1536x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x364x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x364x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x364x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x364x1x1x3x1x768x137x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x364x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x364x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x364x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x364x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x364x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x364x1x1x3x1x80x137x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x365x1x1x1x1x1536x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x365x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x365x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x365x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x365x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x365x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x365x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x365x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x365x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x366x1x1x1x1x1536x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x366x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x366x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x366x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x366x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x366x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x366x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x366x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x366x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x366x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x366x1x1x3x1x80x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x367x1x1x1x1x1536x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x367x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x367x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x367x1x1x1x1x768x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x367x1x1x3x1x768x136x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x367x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x367x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x367x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x367x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x367x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x367x1x1x3x1x80x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x368x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x368x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x368x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x368x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x368x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x368x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x368x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x368x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x368x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x368x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x368x1x1x3x1x80x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x369x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x369x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x369x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x369x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x369x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x369x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x369x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x369x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x369x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x369x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x369x1x1x3x1x80x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x370x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x370x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x370x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x370x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x370x1x1x3x1x768x135x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x370x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x370x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x370x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x370x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x370x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x370x1x1x3x1x80x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x371x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x371x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x371x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x371x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x371x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x371x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x371x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x371x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x371x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x372x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x372x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x372x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x372x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x372x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x372x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x372x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x372x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x372x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x372x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x372x1x1x3x1x80x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x373x1x1x1x1x1536x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x373x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x373x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x373x1x1x1x1x768x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x373x1x1x3x1x768x134x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x373x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x373x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x373x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x373x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x373x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x373x1x1x3x1x80x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x374x1x1x1x1x1536x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x374x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x374x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x374x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x374x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x374x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x374x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x374x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x374x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x374x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x374x1x1x3x1x80x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x375x1x1x1x1x1536x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x375x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x375x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x375x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x375x1x1x3x1x768x133x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x375x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x375x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x375x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x375x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x375x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x375x1x1x3x1x80x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x376x1x1x1x1x1536x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x376x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x376x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x376x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x376x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x376x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x376x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x376x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x376x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x376x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x376x1x1x3x1x80x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x377x1x1x1x1x1536x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x377x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x377x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x377x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x377x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x377x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x377x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x377x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x377x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x377x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x377x1x1x3x1x80x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x378x1x1x1x1x1536x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x378x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x378x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x378x1x1x1x1x768x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x378x1x1x3x1x768x132x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x378x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x378x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x378x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x378x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x378x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x378x1x1x3x1x80x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x379x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x379x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x379x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x379x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x379x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x379x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x379x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x379x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x379x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x37x1x1x1x1x1536x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x37x1x1x1x1x768x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x37x1x1x1x1x768x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x37x1x1x1x1x768x675x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x37x1x1x3x1x768x675x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x37x1x1x3x1x768x675x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x37x1x1x3x1x768x675x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x37x1x1x3x1x768x675x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x37x1x1x3x1x768x675x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x380x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x380x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x380x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x380x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x380x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x380x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x380x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x380x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x380x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x380x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x380x1x1x3x1x80x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x381x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x381x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x381x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x381x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x381x1x1x3x1x768x131x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x381x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x381x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x381x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x381x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x381x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x381x1x1x3x1x80x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x382x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x382x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x382x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x382x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x382x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x382x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x382x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x382x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x382x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x382x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x382x1x1x3x1x80x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x383x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x383x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x383x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x383x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x383x1x1x3x1x768x130x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x383x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x383x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x383x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x383x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x383x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x383x1x1x3x1x80x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x384x1x1x1x1x1536x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x384x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x384x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x384x1x1x1x1x768x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x384x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x384x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x384x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x384x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x384x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x385x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x385x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x385x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x385x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x385x1x1x3x1x768x129x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x385x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x385x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x385x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x385x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x385x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x385x1x1x3x1x80x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x386x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x386x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x386x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x386x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x386x1x1x3x1x768x129x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x386x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x386x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x386x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x386x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x386x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x386x1x1x3x1x80x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x387x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x387x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x387x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x387x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x387x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x387x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x387x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x387x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x387x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x388x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x388x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x388x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x388x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x388x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x388x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x388x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x388x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x388x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x388x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x388x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x388x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x388x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x389x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x389x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x389x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x389x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x389x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x389x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x389x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x389x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x389x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x389x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x389x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x389x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x389x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x38x1x1x1x1x1536x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x38x1x1x1x1x768x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x38x1x1x1x1x768x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x38x1x1x1x1x768x657x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x38x1x1x3x1x768x657x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x38x1x1x3x1x768x657x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x38x1x1x3x1x768x657x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x38x1x1x3x1x768x657x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x38x1x1x3x1x768x657x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x390x1x1x1x1x1536x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x390x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x390x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x390x1x1x1x1x768x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x390x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x390x1x1x3x1x768x128x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x390x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x390x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x390x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x390x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x390x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x390x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x390x1x1x3x1x80x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x391x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x391x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x391x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x391x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x391x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x391x1x1x3x1x80x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x391x1x1x3x1x80x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x392x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x392x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x392x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x392x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x392x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x392x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x392x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x392x1x1x3x1x80x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x392x1x1x3x1x80x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x393x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x393x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x393x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x393x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x393x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x393x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x393x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x393x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x393x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x394x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x394x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x394x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x394x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x394x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x394x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x394x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x394x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x394x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x394x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x394x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x394x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x394x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x395x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x395x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x395x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x395x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x395x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x395x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x395x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x395x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x395x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x395x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x395x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x395x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x395x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x396x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x396x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x396x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x396x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x396x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x396x1x1x3x1x768x126x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x396x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x396x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x396x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x396x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x396x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x396x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x396x1x1x3x1x80x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x397x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x1536x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x397x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x1x1x768x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x397x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x397x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x397x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x397x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x397x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x397x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x397x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x397x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x397x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x398x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x398x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x398x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x398x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x398x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x398x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x398x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x398x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x399x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x399x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x399x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x39x1x1x1x1x1536x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x1x1x1536x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x1x1x768x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x39x1x1x1x1x768x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x1x1x768x641x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x39x1x1x1x1x768x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x39x1x1x1x1x768x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x1x1x768x649x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x39x1x1x3x1x768x641x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x39x1x1x3x1x768x641x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x3x1x768x641x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x39x1x1x3x1x768x641x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x39x1x1x3x1x768x641x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x39x1x1x3x1x768x649x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x39x1x1x3x1x768x649x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x39x1x1x3x1x768x649x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x39x1x1x3x1x768x649x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x39x1x1x3x1x768x649x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x400x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x400x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x3x1x768x125x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x400x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x400x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x400x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x400x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x400x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x400x1x1x3x1x80x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x401x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x401x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x401x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x401x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x402x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x402x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x402x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x402x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x402x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x402x1x1x3x1x80x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x402x1x1x3x1x80x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x403x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x1x1x1536x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x1x1x768x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x403x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x3x1x768x124x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x403x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x403x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x403x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x403x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x403x1x1x3x1x80x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x403x1x1x3x1x80x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x404x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x404x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x404x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x404x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x404x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x404x1x1x3x1x80x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x404x1x1x3x1x80x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x405x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x405x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x405x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x405x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x405x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x406x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x406x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x3x1x768x123x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x406x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x406x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x406x1x1x3x1x80x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x406x1x1x3x1x80x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x407x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x407x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x407x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x407x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x407x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x407x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x407x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x408x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x408x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x3x1x768x122x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x408x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x408x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x408x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x408x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x408x1x1x3x1x80x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x408x1x1x3x1x80x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x409x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x409x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x409x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x40x1x1x1x1x1536x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x40x1x1x1x1x768x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x40x1x1x1x1x768x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x40x1x1x1x1x768x632x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x40x1x1x3x1x768x632x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x40x1x1x3x1x768x632x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x40x1x1x3x1x768x632x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x40x1x1x3x1x768x632x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x40x1x1x3x1x768x632x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x410x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x410x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x1x1x1536x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x1x1x768x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x410x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x410x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x410x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x410x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x410x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x410x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x410x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x411x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x411x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x411x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x411x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x411x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x411x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x411x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x411x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x411x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x412x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x412x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x412x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x412x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x412x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x412x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x412x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x412x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x412x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x412x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x412x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x412x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x412x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x413x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x413x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x413x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x413x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x413x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x413x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x413x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x413x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x413x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x413x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x413x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x413x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x413x1x1x3x1x80x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x414x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x414x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x414x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x414x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x414x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x414x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x414x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x414x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x414x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x414x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x414x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x414x1x1x3x1x80x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x414x1x1x3x1x80x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x415x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x415x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x415x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x415x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x415x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x415x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x415x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x415x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x415x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x416x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x416x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x416x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x416x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x416x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x416x1x1x3x1x768x120x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x416x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x416x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x416x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x416x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x416x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x416x1x1x3x1x80x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x416x1x1x3x1x80x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x417x1x1x1x1x1536x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x417x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x417x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x417x1x1x1x1x768x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x417x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x417x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x417x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x417x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x417x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x417x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x417x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x417x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x417x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x418x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x418x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x418x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x418x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x418x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x418x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x418x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x418x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x418x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x418x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x418x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x418x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x418x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x419x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x419x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x419x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x419x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x419x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x419x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x419x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x419x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x419x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x419x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x419x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x419x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x419x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x420x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x420x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x420x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x420x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x420x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x420x1x1x3x1x768x119x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x420x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x420x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x420x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x420x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x420x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x420x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x420x1x1x3x1x80x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x421x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x421x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x421x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x421x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x421x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x421x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x421x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x421x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x421x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x421x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x421x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x421x1x1x3x1x80x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x421x1x1x3x1x80x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x422x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x422x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x422x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x422x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x422x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x422x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x422x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x422x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x422x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x423x1x1x1x1x1536x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x423x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x423x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x423x1x1x1x1x768x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x423x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x423x1x1x3x1x768x118x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x423x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x423x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x423x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x423x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x423x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x423x1x1x3x1x80x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x423x1x1x3x1x80x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x424x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x424x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x424x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x424x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x425x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x425x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x425x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x425x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x425x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x425x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x425x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x426x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x426x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x426x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x426x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x426x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x426x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x426x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x427x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x427x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x427x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x3x1x768x117x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x427x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x427x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x427x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x427x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x427x1x1x3x1x80x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x428x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x428x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x428x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x428x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x428x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x428x1x1x3x1x80x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x428x1x1x3x1x80x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x429x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x429x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x429x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x429x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x42x1x1x1x1x1536x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x42x1x1x1x1x768x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x42x1x1x1x1x768x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x42x1x1x1x1x768x595x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x42x1x1x3x1x768x595x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x42x1x1x3x1x768x595x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x42x1x1x3x1x768x595x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x42x1x1x3x1x768x595x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x42x1x1x3x1x768x595x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x430x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x430x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x3x1x768x116x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x430x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x430x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x430x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x430x1x1x3x1x80x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x430x1x1x3x1x80x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x431x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x1x1x1536x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x1x1x768x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x431x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x431x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x431x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x432x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x432x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x432x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x432x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x432x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x432x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x432x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x432x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x433x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x433x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x433x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x433x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x433x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x433x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x433x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x433x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x434x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x434x1x1x3x1x768x115x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x434x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x434x1x1x3x1x80x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x435x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x435x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x435x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x435x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x435x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x435x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x436x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x436x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x436x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x436x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x436x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x436x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x436x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x437x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x437x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x437x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x437x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x437x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x437x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x437x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x437x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x438x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x1x1x1536x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x438x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x438x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x438x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x438x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x438x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x438x1x1x3x1x80x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x440x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x440x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x440x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x440x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x440x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x440x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x440x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x440x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x441x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x441x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x441x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x441x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x441x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x441x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x441x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x442x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x442x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x3x1x768x113x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x442x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x442x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x442x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x442x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x442x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x442x1x1x3x1x80x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x443x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x443x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x443x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x443x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x443x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x443x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x444x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x444x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x444x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x444x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x444x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x444x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x444x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x445x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x445x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x445x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x445x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x445x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x445x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x445x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x445x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x446x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x1x1x1536x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x446x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x3x1x768x112x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x446x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x446x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x446x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x446x1x1x3x1x80x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x447x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x447x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x447x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x447x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x447x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x447x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x447x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x448x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x448x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x448x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x448x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x448x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x448x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x449x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x449x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x449x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x449x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x450x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x450x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x3x1x768x111x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x450x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x450x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x450x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x450x1x1x3x1x80x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x451x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x451x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x451x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x451x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x451x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x452x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x452x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x452x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x452x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x452x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x452x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x452x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x453x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x453x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x453x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x453x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x453x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x453x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x453x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x453x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x453x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x454x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x454x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x3x1x768x110x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x454x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x454x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x454x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x454x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x454x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x454x1x1x3x1x80x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x455x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x455x1x1x1x1x1536x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x455x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x455x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x455x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x455x1x1x3x1x80x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x456x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x456x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x456x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x456x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x456x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x456x1x1x3x1x80x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x457x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x457x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x457x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x457x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x458x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x458x1x1x3x1x768x109x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x458x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x458x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x458x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x458x1x1x3x1x80x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x459x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x459x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x459x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x459x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x459x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x459x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x459x1x1x3x1x80x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x45x1x1x1x1x1536x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x1x1x1536x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x45x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x45x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x460x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x460x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x460x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x460x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x460x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x460x1x1x3x1x80x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x462x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x1x1x1536x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x462x1x1x3x1x768x108x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x462x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x462x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x462x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x462x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x462x1x1x3x1x80x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x463x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x463x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x463x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x463x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x463x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x463x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x463x1x1x3x1x80x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x464x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x464x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x464x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x464x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x464x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x464x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x464x1x1x3x1x80x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x465x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x465x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x465x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x465x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x465x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x465x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x465x1x1x3x1x80x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x466x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x466x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x466x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x466x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x466x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x466x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x466x1x1x3x1x80x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x467x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x467x1x1x3x1x768x107x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x467x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x467x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x467x1x1x3x1x80x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x468x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x468x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x468x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x468x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x468x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x468x1x1x3x1x80x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x469x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x469x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x469x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x469x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x46x1x1x1x1x1536x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x1x1x1536x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x1x1x768x543x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x46x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x46x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x46x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x46x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x470x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x470x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x470x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x470x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x470x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x470x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x470x1x1x3x1x80x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x471x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x471x1x1x3x1x768x106x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x471x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x471x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x471x1x1x3x1x80x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x472x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x1536x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x472x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x472x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x472x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x472x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x472x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x472x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x472x1x1x3x1x80x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x473x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x473x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x473x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x473x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x473x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x473x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x473x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x473x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x473x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x474x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x474x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x474x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x474x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x474x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x474x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x474x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x474x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x474x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x474x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x474x1x1x3x1x80x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x475x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x475x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x475x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x475x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x475x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x475x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x475x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x475x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x475x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x476x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x476x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x476x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x476x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x476x1x1x3x1x768x105x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x476x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x476x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x476x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x476x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x476x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x476x1x1x3x1x80x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x477x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x477x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x477x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x477x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x477x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x477x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x477x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x477x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x477x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x477x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x477x1x1x3x1x80x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x478x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x478x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x478x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x478x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x478x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x478x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x478x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x478x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x478x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x478x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x478x1x1x3x1x80x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x479x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x479x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x479x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x479x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x479x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x479x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x479x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x479x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x479x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x479x1x1x3x1x80x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x480x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x480x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x480x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x480x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x480x1x1x3x1x768x104x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x480x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x480x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x480x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x480x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x480x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x480x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x480x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x480x1x1x3x1x80x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x481x1x1x1x1x1536x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x481x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x481x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x481x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x481x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x481x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x481x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x481x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x481x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x481x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x481x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x482x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x482x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x482x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x482x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x482x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x482x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x482x1x1x3x1x80x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x483x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x483x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x483x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x483x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x484x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x484x1x1x3x1x768x103x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x484x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x484x1x1x3x1x80x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x485x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x485x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x485x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x485x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x485x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x486x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x486x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x486x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x486x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x486x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x486x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x486x1x1x3x1x80x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x487x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x487x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x487x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x488x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x488x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x488x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x488x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x488x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x488x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x488x1x1x3x1x80x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x489x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x489x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x489x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x48x1x1x1x1x1536x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x48x1x1x1x1x1536x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x48x1x1x1x1x768x520x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x48x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x48x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x48x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x490x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x1x1x1536x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x1x1x768x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x490x1x1x3x1x768x102x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x490x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x490x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x490x1x1x3x1x80x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x491x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x491x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x491x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x491x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x491x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x492x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x492x1x1x3x1x80x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x493x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x493x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x493x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x493x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x493x1x1x3x1x80x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x494x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x494x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x494x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x494x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x494x1x1x3x1x80x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x495x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x495x1x1x3x1x768x101x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x495x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x495x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x495x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x495x1x1x3x1x80x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x496x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x496x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x496x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x496x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x496x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x496x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x496x1x1x3x1x80x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x497x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x497x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x497x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x497x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x497x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x497x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x497x1x1x3x1x80x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x498x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x498x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x498x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x498x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x498x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x498x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x498x1x1x3x1x80x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x499x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x499x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x499x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x499x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x499x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x499x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x499x1x1x3x1x80x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x500x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x1x1x1536x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x500x1x1x3x1x768x100x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x500x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x500x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x500x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x500x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x500x1x1x3x1x80x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x501x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x501x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x501x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x501x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x501x1x1x3x1x80x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x502x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x502x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x502x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x502x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x502x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x502x1x1x3x1x80x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x503x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x503x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x503x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x503x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x503x1x1x3x1x80x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x504x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x504x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x504x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x504x1x1x3x1x80x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x505x1x1x3x1x768x99x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x505x1x1x3x1x80x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x506x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x506x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x506x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x506x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x506x1x1x3x1x80x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x507x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x507x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x507x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x507x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x507x1x1x3x1x80x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x508x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x508x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x508x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x508x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x508x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x508x1x1x3x1x80x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x509x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x509x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x509x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x509x1x1x3x1x80x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x510x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x1x1x1536x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x510x1x1x3x1x768x49x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x510x1x1x3x1x768x98x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x510x1x1x3x1x80x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x511x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x511x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x511x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x511x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x511x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x511x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x511x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x511x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x511x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x511x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x511x1x1x3x1x80x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x512x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x512x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x512x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x512x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x512x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x512x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x512x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x512x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x512x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x512x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x512x1x1x3x1x80x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x513x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x513x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x513x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x513x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x513x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x513x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x513x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x513x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x513x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x513x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x513x1x1x3x1x80x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x514x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x514x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x514x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x514x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x514x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x514x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x514x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x514x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x514x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x514x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x514x1x1x3x1x80x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x515x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x515x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x515x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x515x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x515x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x515x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x515x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x515x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x515x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x515x1x1x3x1x768x97x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x515x1x1x3x1x80x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x516x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x516x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x516x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x516x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x516x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x516x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x516x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x516x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x516x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x516x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x516x1x1x3x1x80x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x517x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x517x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x517x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x517x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x517x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x517x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x517x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x517x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x517x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x517x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x517x1x1x3x1x80x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x518x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x518x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x518x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x518x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x518x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x518x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x518x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x518x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x518x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x518x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x518x1x1x3x1x80x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x519x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x519x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x519x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x519x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x519x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x519x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x519x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x519x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x519x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x519x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x519x1x1x3x1x80x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x51x1x1x1x1x1536x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x1x1x1536x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x1x1x768x490x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x51x1x1x3x1x768x163x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x51x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x51x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x51x1x1x3x1x768x490x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x51x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x51x1x1x3x1x80x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x768x1x51x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x768x1x520x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x520x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x520x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x520x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x520x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x520x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x520x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x520x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x520x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x520x1x1x3x1x768x96x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x520x1x1x3x1x80x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:163;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x521x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x1536x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x521x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x521x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x1x1x768x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x521x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x521x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x521x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x521x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x521x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x521x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x521x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x521x1x1x3x1x768x48x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x521x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x521x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x522x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x522x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x522x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x522x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x522x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x522x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x522x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x523x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x523x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x523x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x523x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x523x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x523x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x523x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x524x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x524x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x524x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x524x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x524x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x524x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x524x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x525x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x525x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x525x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x525x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x525x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x525x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x525x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x526x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x526x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x526x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x526x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x526x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x526x1x1x3x1x768x95x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x526x1x1x3x1x80x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x527x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x527x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x527x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x527x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x527x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x527x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x527x1x1x3x1x80x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x528x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x528x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x528x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x528x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x528x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x528x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x528x1x1x3x1x80x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x529x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x529x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x529x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x529x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x529x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x529x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x529x1x1x3x1x80x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x52x1x1x1x1x1536x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x52x1x1x1x1x768x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x52x1x1x1x1x768x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x52x1x1x1x1x768x480x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x52x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x52x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x52x1x1x3x1x768x480x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x530x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x530x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x530x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x530x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x530x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x530x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x530x1x1x3x1x80x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x531x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x1x1x1536x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x1x1x768x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x531x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x531x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x531x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x531x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x531x1x1x3x1x768x94x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x531x1x1x3x1x80x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x532x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x532x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x532x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x532x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x532x1x1x3x1x80x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x533x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x533x1x1x3x1x80x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x534x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x534x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x534x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x534x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x535x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x535x1x1x3x1x80x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x536x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x536x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x536x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x536x1x1x3x1x80x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x537x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x537x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x537x1x1x3x1x768x93x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x537x1x1x3x1x80x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x538x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x538x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x539x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x539x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x539x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x539x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x539x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x540x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x540x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x541x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x541x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x541x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x541x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x541x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x542x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x542x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x542x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x542x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x542x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x542x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x543x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x1x1x768x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x543x1x1x3x1x768x46x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x543x1x1x3x1x768x92x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x543x1x1x3x1x80x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x544x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x544x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x544x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x544x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x544x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x545x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x545x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x545x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x545x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x545x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x545x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x546x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x546x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x547x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x547x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x547x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x547x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x548x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x548x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x548x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x548x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x548x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x549x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x549x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x549x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x549x1x1x3x1x768x91x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x549x1x1x3x1x80x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x54x1x1x1x1x1536x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x1x1x1536x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x1x1x768x467x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x54x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x54x1x1x3x1x768x467x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x550x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x550x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x551x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x551x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x551x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x551x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x551x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x551x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x551x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x552x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x552x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x552x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x552x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x552x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x552x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x552x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x553x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x553x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x554x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x554x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x554x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x554x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x554x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x555x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x555x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x555x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x555x1x1x3x1x768x90x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x555x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x556x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x556x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x556x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x556x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x556x1x1x3x1x768x45x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x556x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x556x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x557x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x557x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x557x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x557x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x558x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x558x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x558x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x558x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x558x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x559x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x559x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x559x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x559x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x55x1x1x1x1x1536x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x1x1x1536x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x1x1x768x454x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x55x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x55x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x55x1x1x3x1x768x454x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x560x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x560x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x561x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x561x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x561x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x561x1x1x3x1x768x89x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x561x1x1x3x1x80x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x562x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x562x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x562x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x562x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x562x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x563x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x563x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x564x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x564x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x564x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x564x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x564x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x565x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x565x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x565x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x565x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x565x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x566x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x566x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x567x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x567x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x567x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x567x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x567x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x567x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x567x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x568x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x1x1x1536x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x1x1x768x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x568x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x568x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x568x1x1x3x1x768x44x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x568x1x1x3x1x768x88x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x568x1x1x3x1x80x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x569x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x569x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x569x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x569x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x569x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x570x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x570x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x570x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x570x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x570x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x570x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x571x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x571x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x571x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x571x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x571x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x571x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x571x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x572x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x572x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x572x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x572x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x572x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x572x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x572x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x573x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x573x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x573x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x573x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x573x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x573x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x574x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x574x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x574x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x574x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x574x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x575x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x575x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x575x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x575x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x576x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x576x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x576x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x576x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x576x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x577x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x577x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x577x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x577x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x577x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x578x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x578x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x578x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x578x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x579x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x579x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x579x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x579x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x579x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x57x1x1x1x1x1536x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x1x1x1536x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x57x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x57x1x1x3x1x768x438x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x580x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x580x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x581x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x1x1x1536x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x581x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x581x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x581x1x1x3x1x768x43x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x581x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x581x1x1x3x1x80x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x582x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x582x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x582x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x582x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x582x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x582x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x582x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x583x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x583x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x583x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x583x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x583x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x584x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x584x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x584x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x584x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x584x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x585x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x585x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x586x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x586x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x586x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x586x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x586x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x587x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x587x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x587x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x587x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x587x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x587x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x587x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x588x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x588x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x588x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x588x1x1x3x1x768x85x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x588x1x1x3x1x80x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x589x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x589x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:172;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x58x1x1x1x1x1536x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x1x1x1536x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x1x1x768x434x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x58x1x1x3x1x768x434x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x590x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x590x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x590x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x590x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x590x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x591x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x591x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x592x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x592x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x592x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x592x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x592x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x593x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x593x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x593x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x593x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x593x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x594x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x594x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x595x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x1x1x1536x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x595x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x595x1x1x3x1x768x42x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x595x1x1x3x1x768x84x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x595x1x1x3x1x80x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x596x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x596x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x596x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x596x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x596x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x597x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x597x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x597x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x597x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x597x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x598x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x598x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x599x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x599x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x599x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x599x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x59x1x1x1x1x1536x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x1x1x1536x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x1x1x768x423x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x59x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x59x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x59x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x59x1x1x3x1x768x423x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x600x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x600x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x600x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x600x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x600x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x600x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x600x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x601x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x601x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x601x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x601x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x601x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x602x1x1x3x1x768x83x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x602x1x1x3x1x80x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x603x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x603x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x603x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x603x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x603x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x604x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x604x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x604x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x604x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x604x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x605x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x605x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x605x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x605x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x606x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x606x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x606x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x606x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x607x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x607x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x608x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x608x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x608x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x608x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x609x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x1x1x1536x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x1x1x768x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x609x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x609x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x609x1x1x3x1x768x82x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x609x1x1x3x1x80x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x610x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x610x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x611x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x611x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x611x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x611x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x611x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x611x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x611x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x611x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x611x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x611x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x611x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x612x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x612x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x613x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x613x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x613x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x613x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x613x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x613x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x613x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x613x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x613x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x613x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x614x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x614x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x614x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x614x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x614x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x614x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x614x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x614x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x614x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x614x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x615x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x615x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x616x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x616x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x616x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x616x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x616x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x616x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x616x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x616x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x616x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x617x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x617x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x617x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x617x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x617x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x617x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x617x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x617x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x617x1x1x3x1x768x81x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x617x1x1x3x1x80x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x618x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x618x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x618x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x618x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x618x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x618x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x618x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x618x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x618x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x619x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x619x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x619x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x61x1x1x1x1x1536x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x1x1x1536x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x1x1x768x413x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x61x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x61x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x61x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x61x1x1x3x1x768x413x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x620x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x620x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x621x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x621x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x621x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x621x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x621x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x621x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x621x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x621x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x622x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x622x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x622x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x622x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x622x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x622x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x622x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x622x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x623x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x623x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x624x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x624x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x625x1x1x1x1x1536x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x625x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x625x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x625x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x625x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x625x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x625x1x1x3x1x768x40x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x625x1x1x3x1x768x80x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x625x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x626x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x626x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x627x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x627x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x627x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x627x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x628x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x628x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x628x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x628x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x628x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x629x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x629x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x62x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x62x1x1x3x1x768x462x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x62x1x1x3x1x80x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x62x1x1x3x1x80x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x630x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x630x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x630x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x630x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x630x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x630x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x631x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x631x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x632x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x632x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x632x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x632x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x632x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x632x1x1x3x1x768x79x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x632x1x1x3x1x80x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x634x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x634x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x636x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x636x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x636x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x636x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x636x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x636x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x636x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x637x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x637x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x637x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x637x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x637x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x638x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x638x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x639x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x1x1x1536x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x639x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x639x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x639x1x1x3x1x768x39x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x639x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x639x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x63x1x1x1x1x1536x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x1536x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x1536x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x1536x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x768x396x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x1x1x768x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x63x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x63x1x1x3x1x768x396x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x63x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x63x1x1x3x1x768x400x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x640x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x640x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x641x1x1x3x1x768x78x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x641x1x1x3x1x80x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x642x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x642x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x642x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x642x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x642x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x643x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x643x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x643x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x643x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x644x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x644x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x645x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x645x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x646x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x646x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x647x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x647x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x647x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x647x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x647x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x648x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x648x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x648x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x648x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x648x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x649x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x649x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x649x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x649x1x1x3x1x768x77x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x649x1x1x3x1x80x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x650x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x650x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x650x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x650x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x651x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x651x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x652x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x652x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x652x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x652x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x652x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x652x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x652x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x653x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x653x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x654x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,154[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x654x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x654x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x654x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x656x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x656x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x656x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x656x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x657x1x1x3x1x768x76x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x657x1x1x3x1x80x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x658x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x1x1x1536x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x658x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x658x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x658x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x658x1x1x3x1x768x38x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x658x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x658x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x659x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x659x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x65x1x1x1x1x1536x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x1x1x1536x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x1x1x768x384x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x65x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x65x1x1x3x1x768x384x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x65x1x1x3x1x768x517x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x65x1x1x3x1x80x517x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x660x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x660x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x660x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x660x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x660x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x660x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x661x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x661x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x662x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x662x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x662x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x662x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x662x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x663x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x663x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x664x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x664x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x664x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x664x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x664x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x665x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x665x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x666x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x666x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x666x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x666x1x1x3x1x768x75x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x666x1x1x3x1x80x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x667x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x667x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x667x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x667x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x668x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x668x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x669x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x669x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x670x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x670x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x670x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x670x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x670x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x670x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x670x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x671x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x671x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x671x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x671x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x671x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x672x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x672x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x673x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x673x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x674x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x674x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x675x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x1x1x1536x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x1x1x768x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x675x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x675x1x1x3x1x768x37x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x675x1x1x3x1x768x74x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x675x1x1x3x1x80x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x676x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x676x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x676x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x676x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x676x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x676x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x676x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x677x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x677x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x677x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x677x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x677x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x678x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x678x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x679x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x679x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x67x1x1x1x1x1536x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x1536x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x1536x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x1536x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x768x373x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x1x1x768x375x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x67x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x67x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x373x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x67x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x67x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x67x1x1x3x1x768x375x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x680x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x680x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x681x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x681x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x681x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x681x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x681x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x682x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x682x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x682x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x682x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x682x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x682x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x682x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x683x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x683x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x684x1x1x3x1x768x73x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x684x1x1x3x1x80x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x685x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x685x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x686x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:209;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x686x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x686x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x686x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x686x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x687x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x687x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x688x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x688x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x689x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x689x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x689x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x689x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x689x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x690x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:214;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x690x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x690x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x690x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x690x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x691x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x691x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x692x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x692x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x692x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x692x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x692x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x693x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x1x1x1536x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x693x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x693x1x1x3x1x768x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x693x1x1x3x1x768x72x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x693x1x1x3x1x80x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x695x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x695x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x697x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x697x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x697x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x697x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x698x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x698x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x699x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x699x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x69x1x1x1x1x1536x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x1x1x1536x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x1x1x768x364x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x69x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x69x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x69x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x69x1x1x3x1x768x364x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x700x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x700x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x700x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x700x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x701x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x701x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x702x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x702x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x703x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x703x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x704x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x704x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x704x1x1x3x1x768x71x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x704x1x1x3x1x80x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x705x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x705x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x705x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x705x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x706x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x706x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x707x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x707x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x707x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x708x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x708x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x709x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x709x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x709x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x709x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x70x1x1x1x1x1536x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x1x1x1536x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x1x1x768x357x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x70x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x70x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x70x1x1x3x1x768x357x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x710x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x710x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x710x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x710x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x710x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x711x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x711x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x711x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x711x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x711x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x711x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x711x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x713x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x1x1x1536x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x713x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x713x1x1x3x1x768x35x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x713x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x713x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x714x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x714x1x1x3x1x80x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x715x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x715x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x716x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x716x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x716x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x716x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x716x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x717x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:222;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x717x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x717x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x717x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x717x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x717x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x718x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x718x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x768x1x719x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x719x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x71x1x1x1x1x1536x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x1x1x1536x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x1x1x768x352x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x71x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x71x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x71x1x1x3x1x768x352x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x720x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x720x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x720x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x720x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x720x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x721x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x721x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x722x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x722x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x722x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x722x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x722x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x722x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x723x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x723x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x724x1x1x3x1x768x69x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x724x1x1x3x1x80x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x725x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x725x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x726x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x726x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x726x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x726x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x726x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x726x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x726x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x726x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x727x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:227;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x727x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x727x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x727x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x728x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x728x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x728x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x728x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x729x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x729x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x730x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x730x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x731x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x731x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x732x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x732x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x732x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x732x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x732x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x733x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x733x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x734x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x734x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x734x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x734x1x1x3x1x768x68x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x734x1x1x3x1x80x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x735x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x1x1x1536x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x1x1x768x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x735x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x735x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x735x1x1x3x1x768x34x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x736x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x736x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x737x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x737x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x737x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x737x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x737x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x737x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x737x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x737x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x738x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x738x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x738x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x738x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x738x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x738x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x738x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x738x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x739x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x739x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+16
2x768x1x740x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x740x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x740x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x740x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x740x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x740x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x740x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x740x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x740x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x740x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x740x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x742x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x742x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x743x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x743x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x744x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x744x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x744x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x744x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x744x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x744x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x744x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x744x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x744x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x744x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x744x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x745x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x745x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x746x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x746x1x1x3x1x80x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x747x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x747x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x748x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x748x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x748x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x748x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x748x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x748x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x748x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x748x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x748x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x749x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x749x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x74x1x1x1x1x1536x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x1x1x1536x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x1x1x768x337x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x74x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x74x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x74x1x1x3x1x768x337x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x74x1x1x3x1x768x675x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x74x1x1x3x1x80x675x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x750x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x750x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x750x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x750x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x750x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x750x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x750x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x750x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x750x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x751x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x751x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x751x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x751x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x751x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x751x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x751x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x751x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x751x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x752x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x752x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x753x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x753x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x754x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x754x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x754x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x754x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x754x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x754x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x754x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x754x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x754x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x755x1x1x1x1x1536x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x755x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x755x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x755x1x1x1x1x768x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x755x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x755x1x1x3x1x768x33x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x755x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x755x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x756x1x1x3x1x768x66x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x756x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x758x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x758x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x758x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x758x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x758x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x759x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x759x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x75x1x1x1x1x1536x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x1536x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x1536x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x1536x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x768x333x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x1x1x768x335x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:203;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x75x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x75x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x333x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x75x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x75x1x1x3x1x768x335x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x760x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x760x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x761x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x761x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x761x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x761x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x761x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x762x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x762x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x762x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x762x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x764x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x764x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x764x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x764x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x765x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x765x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x767x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x767x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x767x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x767x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x767x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x768x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x768x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x768x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x768x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x768x1x1x3x1x768x65x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x768x1x1x3x1x80x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x76x1x1x3x1x768x657x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x76x1x1x3x1x80x657x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x770x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x770x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x770x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x770x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x772x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x772x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x772x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x772x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x772x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x773x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x773x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x774x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x774x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x774x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x774x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x775x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x775x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x776x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x776x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x776x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x776x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x776x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x777x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x777x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x778x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x778x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x778x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x778x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x779x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x779x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x77x1x1x1x1x1536x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x77x1x1x1x1x768x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x77x1x1x1x1x768x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x77x1x1x1x1x768x324x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x77x1x1x3x1x768x324x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x77x1x1x3x1x768x324x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x77x1x1x3x1x768x324x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x77x1x1x3x1x768x324x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x77x1x1x3x1x768x324x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x77x1x1x3x1x768x649x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x77x1x1x3x1x80x649x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x780x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x780x1x1x3x1x80x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x781x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x1x1x1536x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x781x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x781x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x781x1x1x3x1x768x32x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x782x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x782x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x783x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x783x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x785x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x785x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x785x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x785x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x785x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x785x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x785x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x786x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x786x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x787x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x787x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x787x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x787x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x787x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x787x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x789x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x789x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x78x1x1x1x1x1536x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x78x1x1x1x1x768x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x78x1x1x1x1x768x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x78x1x1x1x1x768x322x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x78x1x1x3x1x768x322x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x78x1x1x3x1x768x322x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x78x1x1x3x1x768x322x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x78x1x1x3x1x768x322x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x78x1x1x3x1x768x322x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x78x1x1x3x1x768x641x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x78x1x1x3x1x80x641x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x790x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x790x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x792x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x792x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x793x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x793x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x793x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x793x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x793x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x793x1x1x3x1x80x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x794x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x794x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x794x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x794x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x794x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x794x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x794x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x795x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x795x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x795x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x795x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x796x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x796x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x796x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x796x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:170;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x797x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x797x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x797x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x797x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x797x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x798x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x798x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x798x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x798x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x79x1x1x3x1x768x632x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x79x1x1x3x1x80x632x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x800x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x800x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x800x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x800x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x801x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x801x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x801x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x801x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x802x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x802x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x802x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x802x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x802x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x802x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x803x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x803x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x803x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x804x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x804x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x804x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x804x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x804x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x804x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x804x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x805x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x1x1x1536x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x1x1x768x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x805x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x805x1x1x3x1x768x31x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x805x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x805x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x805x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x806x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x806x1x1x3x1x768x62x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x806x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x806x1x1x3x1x80x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:173;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x807x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x807x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x807x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x807x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x808x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x808x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x808x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x808x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x80x1x1x1x1x1536x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x1536x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x1536x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x1536x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x768x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x1x1x768x314x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x80x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x312x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x80x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x80x1x1x3x1x768x314x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x810x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x810x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x810x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x810x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x811x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x811x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x811x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x811x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x812x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x812x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x812x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x812x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x813x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:212;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:241;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x813x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x813x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x813x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x813x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x813x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x813x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x814x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:243;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x814x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x814x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x814x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x814x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x814x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x815x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:221;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x815x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x815x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x815x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x815x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x815x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x816x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x816x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x816x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x816x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x818x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:202;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x818x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x818x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x818x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x818x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x818x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x819x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x819x1x1x3x1x768x61x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x819x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x819x1x1x3x1x80x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x820x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x820x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x822x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x822x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x823x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x823x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x823x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x823x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x824x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x824x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x824x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x824x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x824x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x825x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x825x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x826x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x826x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x826x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x826x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x826x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x826x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x827x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x827x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x827x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x827x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x827x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x828x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x828x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x829x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x829x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x82x1x1x1x1x1536x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x1x1x1536x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x1x1x768x304x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x82x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x82x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x82x1x1x3x1x768x304x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x830x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x830x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x830x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x830x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x830x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x831x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x1x1x1536x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x1x1x768x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:247;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x831x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x831x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x831x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x831x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x831x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x832x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x832x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x833x1x1x3x1x768x60x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x833x1x1x3x1x80x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x835x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x835x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x836x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x836x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x837x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x837x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x838x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x838x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x838x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x838x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x838x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x839x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x839x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x83x1x1x1x1x1536x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x1x1x1536x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x1x1x768x301x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x83x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x83x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x83x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x83x1x1x3x1x768x301x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x840x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x840x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x840x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x840x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x840x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x841x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x841x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x842x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x842x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x843x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x843x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x844x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x844x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x845x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x845x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x846x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x846x1x1x3x1x80x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x848x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x848x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x849x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x849x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x849x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x849x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x849x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x849x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x84x1x1x3x1x768x595x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x84x1x1x3x1x80x595x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x850x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x850x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x851x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x851x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x852x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x852x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x852x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x852x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x853x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x853x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x854x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x854x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x854x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x854x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x854x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x856x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x856x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x857x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x857x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x858x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x858x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x859x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x859x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x85x1x1x1x1x1536x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x1536x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x1536x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x1536x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x768x294x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x1x1x768x295x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x85x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x294x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x85x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x85x1x1x3x1x768x295x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x860x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x860x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x861x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x861x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x861x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x861x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x861x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x861x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x862x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x1x1x1536x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x862x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x862x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x862x1x1x3x1x768x29x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x862x1x1x3x1x768x58x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x862x1x1x3x1x80x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x863x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x863x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x863x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x863x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x864x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x864x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x864x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x864x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x865x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x865x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x865x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x865x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x866x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x866x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x866x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x866x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x867x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x867x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x867x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x867x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x869x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x869x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x869x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x869x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x86x1x1x1x1x1536x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x1x1x1536x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x1x1x768x290x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x86x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x86x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x86x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x86x1x1x3x1x768x290x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x870x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x870x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x870x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x870x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x872x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x872x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x872x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x872x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x873x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x873x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x873x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x873x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x874x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x874x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x874x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x874x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x875x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x875x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x875x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x875x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x876x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x876x1x1x3x1x768x57x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x876x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x876x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x879x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x879x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x879x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x879x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x87x1x1x1x1x1536x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x1x1x1536x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x1x1x768x287x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x87x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x87x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x87x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x87x1x1x3x1x768x287x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x880x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x880x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x880x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x880x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x880x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x882x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x882x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x882x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x882x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x883x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x883x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x883x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x883x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x884x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x884x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x884x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x884x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x885x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x885x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x885x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x885x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x886x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x886x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x886x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x886x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x887x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x887x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x887x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x887x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x888x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x888x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x888x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x888x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x889x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x889x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x889x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x889x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x88x1x1x1x1x1536x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x1x1x1536x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x1x1x768x284x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x88x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x88x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x88x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x891x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x891x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x891x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x891x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x891x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x891x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x891x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x892x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x1x1x1536x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x1x1x768x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x892x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x892x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x892x1x1x3x1x768x28x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x892x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x3x1x768x56x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x892x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x892x1x1x3x1x80x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x893x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,1,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,161[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x893x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x893x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x893x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x893x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x893x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x894x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x894x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x894x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x894x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x895x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x895x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x895x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x895x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x896x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x896x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x896x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x896x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x896x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x896x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x898x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x898x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x898x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x898x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x899x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x899x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x899x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x899x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x89x1x1x1x1x1536x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x1x1x1536x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x1x1x768x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:194;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x89x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x89x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x89x1x1x3x1x768x280x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x89x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x3x1x768x561x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x89x1x1x3x1x80x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x89x1x1x3x1x80x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x901x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x901x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x901x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x901x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x902x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x902x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x902x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x902x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x903x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x903x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x903x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x903x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x904x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x904x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x904x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x904x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x905x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x905x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x905x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x905x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x906x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x906x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x906x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x906x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x908x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x908x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x908x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x908x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x909x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x909x1x1x3x1x768x55x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x909x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x909x1x1x3x1x80x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:180;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x90x1x1x1x1x1536x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x90x1x1x1x1x1536x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x90x1x1x1x1x768x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x90x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x90x1x1x3x1x768x277x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x911x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x911x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:246;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x911x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x911x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x912x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x912x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x912x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x912x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x912x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x913x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x913x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x913x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x913x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x914x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x914x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x914x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x914x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x915x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x915x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x915x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x915x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x916x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x916x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x916x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x916x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x917x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x917x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x917x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x917x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x917x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x918x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x918x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x918x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x918x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x919x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x919x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x919x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x919x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x91x1x1x1x1x1536x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x1536x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x1536x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x1536x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x768x274x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x1x1x768x276x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x91x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x274x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x91x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x91x1x1x3x1x768x276x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x920x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x920x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x920x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x920x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x920x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x920x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x923x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x923x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x923x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x923x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x924x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x1x1x1536x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,159[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x924x1x1x3x1x768x27x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x924x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x3x1x768x54x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x924x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x924x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x926x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x926x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x926x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x926x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x926x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x928x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x928x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x928x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x928x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x929x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x929x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x929x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x929x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x92x1x1x1x1x1536x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x1x1x1536x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x1x1x768x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x92x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x92x1x1x3x1x768x271x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x92x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x3x1x768x543x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x92x1x1x3x1x80x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x92x1x1x3x1x80x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x931x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x931x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x931x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x931x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x932x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x932x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x932x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x932x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x933x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x933x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x933x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x933x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x934x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x934x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x934x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x934x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x935x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x935x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x935x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x935x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x935x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x935x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x935x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x938x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x938x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x938x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x938x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x939x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x939x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x939x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x939x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x93x1x1x1x1x1536x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x1x1x1536x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x1x1x768x268x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x93x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x93x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x93x1x1x3x1x768x268x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x941x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:215;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x941x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x941x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x941x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x941x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x941x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x942x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:230;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x942x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x942x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x942x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x943x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x943x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x943x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x943x1x1x3x1x80x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x944x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x944x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x946x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x946x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x947x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x947x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x948x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x948x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x949x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x949x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x94x1x1x1x1x1536x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x1x1x1536x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x1x1x768x265x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x94x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x94x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x94x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x94x1x1x3x1x768x265x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x950x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x950x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x951x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:195;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x951x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x951x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x951x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x951x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x952x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x952x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x953x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x953x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x954x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x954x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x955x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x955x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:87;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x957x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x957x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x957x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x958x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x958x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x958x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x958x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x958x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x958x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x959x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x1x1x1536x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x1x1x768x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:208;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x959x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x959x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x959x1x1x3x1x768x26x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x959x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x959x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x95x1x1x1x1x1536x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x1x1x1536x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x1x1x768x263x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x95x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x95x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x95x1x1x3x1x768x263x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x960x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x960x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x960x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x961x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x961x1x1x3x1x768x52x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x961x1x1x3x1x80x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x963x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x963x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x963x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x963x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x964x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x964x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x964x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x964x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x965x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x965x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x965x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x965x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x966x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x966x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x966x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x966x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x967x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x967x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x967x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x967x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x969x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x969x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x969x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x969x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x96x1x1x1x1x1536x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x1x1x1536x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x1x1x768x260x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x96x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x96x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x96x1x1x3x1x768x260x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x96x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x3x1x768x520x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x96x1x1x3x1x80x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x96x1x1x3x1x80x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x971x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x971x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x971x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x971x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x972x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x972x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x972x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x972x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x973x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x973x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x973x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x973x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x974x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x974x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x974x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x974x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x976x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x976x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x976x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x976x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x978x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x978x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x978x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x978x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x979x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x979x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x97x1x1x1x1x1536x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x1x1x1536x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x1x1x768x257x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x97x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:238;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x97x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x97x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x97x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x97x1x1x3x1x768x257x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x980x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,147[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x980x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x980x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x980x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x980x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x980x1x1x3x1x80x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x982x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x982x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x982x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x982x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x986x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x986x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x986x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x986x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x987x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x987x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x987x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x987x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x989x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x989x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x989x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x989x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x98x1x1x1x1x1536x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x1x1x1536x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x1x1x768x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:217;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x98x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x98x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x98x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x98x1x1x3x1x768x255x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x990x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x990x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x990x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x990x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x990x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x990x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x991x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:250;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x991x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x991x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,61[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x991x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x991x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x991x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x993x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x993x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x993x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x993x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x994x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x994x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x994x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x994x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,5,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[5];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x996x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x996x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x996x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x996x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x997x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x997x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x997x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x997x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x997x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x998x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x998x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x998x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x998x1x1x3x1x80x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:206;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x768x1x999x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x1x1x1536x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x999x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x999x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x999x1x1x3x1x768x25x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x99x1x1x1x1x1536x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x1x1x1536x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x1x1x768x252x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:200;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x1x99x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,67[2];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+2
2x768x1x99x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x1x99x1x1x3x1x768x252x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x2048x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x768x24x24x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x24x24x1x2x2x1x1536x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x24x24x1x7x7x1x768x1x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x256x256x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x256x256x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x256x256x1x1x1x1x640x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x256x256x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x256x256x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x256x256x1x3x3x1x768x4x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x257x257x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x257x257x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x25x25x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x28x28x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x28x28x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x28x28x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x768x28x28x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x768x28x28x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x292x292x1x7x7x1x768x4x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x29x29x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x29x29x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x29x29x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x29x29x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x768x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x30x46x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:168;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+4
2x768x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x30x46x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:252;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x768x32x32x1x1x1x1x140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x32x32x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x1x1x1x2304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x32x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x32x32x1x1x1x1x6144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x32x32x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[3];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x3x3x1x768x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x32x32x1x3x3x1x768x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[3];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x32x32x1x5x5x1x768x1x2x2x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x32x32x1x7x7x1x768x1x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x37x37x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x37x37x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x48x32x1x3x3x1x2048x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x48x32x1x3x3x1x2048x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x48x32x1x3x3x1x2048x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x32x1x3x3x1x2048x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x48x48x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x4x16x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x4x4x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x4x4x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x50x50x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x768x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x512x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:233
2x768x512x512x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x512x512x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x55x55x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x56x56x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x56x56x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x56x56x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x56x56x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x57x57x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x62x62x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x64x64x1x1x1x1x140x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x64x64x1x1x1x1x1539x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x768x64x64x1x1x1x1x1540x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x64x64x1x1x1x1x1541x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x768x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,143[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x64x64x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x768x64x64x1x1x1x1x2176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x1x1x1x2560x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x64x64x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x64x64x1x1x1x1x768x1x0x0x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x64x64x1x2x2x1x1536x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,147[2];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[2];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x64x64x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x64x64x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x64x64x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x64x64x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x64x64x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x48xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x768x64x64x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x64x64x1x5x1x1x768x1x2x0x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x64x64x1x7x7x1x768x4x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x768x6x6x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x6x6x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x768x6x6x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x768x6x6x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x768x6x6x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x768x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x768x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[2];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x768x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22[2];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x768x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[2];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x768x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,194;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,175[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:99;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x768x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x768x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x1539x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x768x7x7x1x1x1x1x2176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[3];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x1x1x2176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x2432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,3,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[3];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x7x7x1x1x1x1x2432x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x768x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,240[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,2,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,155[2];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x768x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x248x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x768x7x7x1x1x1x1x2560x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,3,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,73[3];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x768x7x7x1x1x1x1x2560x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,36;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x768x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,3,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x7x7x1x1x1x1x4608x1x0x0x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x1x5x1x768x1x0x2x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x1x5x1x768x4x0x2x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x768x7x7x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x7x7x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x768x7x7x1x2x2x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x3x3x1x768x128x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x768x7x7x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x3x3x1x768x16x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x768x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x768x7x7x1x3x3x1x768x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x768x7x7x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x768x7x7x1x3x3x1x768x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x768x7x7x1x3x3x1x768x98x1x1x0x1x1x0x1x1x0x0x768xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x3x3x1x768x98x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x7x7x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x768x7x7x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x16x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x768x7x7x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x768x7x7x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x32x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x768x7x7x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x768x7x7x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x768x7x7x1x5x5x1x768x64x2x2x0x2x2x0x1x1x0x0x768xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x768x7x7x1x7x7x1x768x4x3x3x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x768x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,61[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x768x8x8x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,49[7];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x768x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x768x8x8x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,2,1,16,1,16,48;ConvBinWinogradRxSf2x3:248;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x768x8x8x1x1x1x1x1536x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x8x8x1x1x1x1x3072x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x768x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x8x8x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,3,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x768x8x8x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x768x8x8x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x768x8x8x1x3x3x1x768x4x0x0x0x1x1x0x1x1x0x0x768xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x76x112x112x1x1x1x1x76x1x0x0x0x2x2x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x76x1x1x1x1x1x1x1216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x256x256x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x256x256x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x256x256x1x1x1x1x76x1x0x0x0x1x1x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x76x256x256x1x3x3x1x152x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x512x512x1x1x1x1x76x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x512x512x1x1x1x1x76x1x0x0x0x2x2x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x76x512x512x1x1x1x1x76x4x0x0x0x1x1x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x512x512x1x3x3x1x76x1x1x1x0x2x2x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x512x512x1x3x3x1x76x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x512x512x1x3x3x1x76x4x1x1x0x1x1x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x56x56x1x1x1x1x76x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x56x56x1x3x3x1x152x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x56x56x1x3x3x1x152x1x1x1x0x2x2x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x56x56x1x3x3x1x152x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x56x56x1x3x3x1x76x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x56x56x1x3x3x1x76x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x76x56x56x1x3x3x1x76x4x1x1x0x1x1x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x76x64x64x1x3x3x1x76x1x1x1x0x1x1x0x1x1x0x0x76xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x77x56x56x1x1x1x1x462x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x784x128x128x1x1x1x1x1624x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x784x14x14x1x1x1x1x1624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x784x14x14x1x3x3x1x784x1x1x1x0x1x1x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x784x14x14x1x3x3x1x784x4x1x1x0x2x2x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x784x1x1x1x1x1x1x196x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x784x28x28x1x3x3x1x784x1x1x1x0x2x2x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x784x28x28x1x3x3x1x784x4x1x1x0x2x2x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x784x64x64x1x1x1x1x1624x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x784x64x64x1x1x1x1x784x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x784x64x64x1x3x3x1x784x1x1x1x0x1x1x0x1x1x0x0x14xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x784x64x64x1x3x3x1x784x1x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x784x64x64x1x3x3x1x784x4x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x784x7x7x1x3x3x1x784x1x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x784x7x7x1x3x3x1x784x4x1x1x0x1x1x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x78x256x256x1x1x1x1x142x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x78x256x256x1x3x3x1x78x4x1x1x0x1x1x0x1x1x0x0x78xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x78x28x28x1x1x1x1x142x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x78x28x28x1x1x1x1x142x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x78x28x28x1x3x3x1x78x1x1x1x0x1x1x0x1x1x0x0x78xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x798x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x79x1x1x1x1x1x1x954x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x79x256x256x1x1x1x1x474x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7x128x128x1x3x3x1x7x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7x14x14x1x3x3x1x7x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7x14x14x1x3x3x1x7x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7x256x256x1x3x3x1x7x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x7x28x28x1x3x3x1x7x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x800x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x800x128x128x1x3x3x1x800x1x1x1x0x1x1x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x800x128x128x1x3x3x1x800x1x1x1x0x2x2x0x1x1x0x0x50xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x800x14x14x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x800x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x800x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x800x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:109;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x800x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x800x256x256x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x800x64x64x1x1x1x1x1088x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x64x64x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x800x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x800x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x800x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:176;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:107;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x800x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x800x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:103;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x800x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x800x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x800x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x802x17x17x1x5x5x1x802x4x0x0x0x2x2x0x1x1x0x0x802xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x802x1x1x1x1x1x1x34x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x802x32x32x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x802x64x64x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x802x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x806x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x806x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x806x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x806x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x806x7x7x1x5x5x1x806x1x2x2x0x1x1x0x1x1x0x0x806xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x806x7x7x1x5x5x1x806x4x2x2x0x1x1x0x1x1x0x0x806xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x80x1024x1024x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1024x1024x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1024x1024x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x1024x1024x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1024x1024x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:255;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x112x112x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x112x112x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x112x112x1x1x1x1x80x4x0x0x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x112x112x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x112x112x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x112x112x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x112x112x1x5x5x1x80x4x2x2x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x128x128x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x128x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x171x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x80x128x128x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x200x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x52x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x128x128x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x128x128x1x1x1x1x92x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x128x128x1x2x2x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x80x128x128x1x3x3x1x320x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x128x128x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x128x128x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x128x128x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x128x128x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x80x128x128x1x5x5x1x80x1x2x2x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x14x14x1x1x1x1x100x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x14x14x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x80x14x14x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x14x14x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x80x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,260;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,0,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,131;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x80x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x14x14x1x1x1x1x92x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x150x150x1x1x1x1x2560x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x150x150x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x15x15x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x16x16x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1000x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1000x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1001x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1001x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1004x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1004x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1006x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1006x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1008x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1008x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1011x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1011x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1012x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1012x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1014x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1014x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1015x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1015x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1016x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1016x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1018x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1018x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1019x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1019x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1020x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1020x1x1x3x1x768x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1021x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1022x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1023x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1026x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1027x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x102x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x102x1x1x3x1x768x490x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1030x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1031x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1033x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1034x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1035x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1036x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1038x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1040x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1041x1x1x3x1x768x48x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1042x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1043x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1044x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1045x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1047x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1048x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x104x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x104x1x1x3x1x768x480x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1050x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1051x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1052x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1054x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1055x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1057x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1058x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1059x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1060x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1061x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1062x1x1x3x1x768x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1064x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1064x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1067x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x1067x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1068x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1068x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1071x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1071x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1072x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1072x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1073x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1073x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1077x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1077x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1078x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1078x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x107x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x107x1x1x3x1x768x467x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1081x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1081x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1082x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1082x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1084x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1084x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1085x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1085x1x1x3x1x768x46x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1087x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1087x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1088x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1088x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1090x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1090x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1093x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1093x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1094x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1094x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1095x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1095x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1096x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1096x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1097x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1097x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1101x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1101x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1102x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1102x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1103x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1103x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1107x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1107x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1109x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1109x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x110x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x110x1x1x3x1x768x454x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1111x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1111x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1112x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1112x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1114x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1114x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1115x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1115x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1116x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1116x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1118x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1118x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1121x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1121x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1122x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1122x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1123x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1123x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1128x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1128x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1129x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1129x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1134x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1134x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1135x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1135x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1138x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1138x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1140x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1140x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1141x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1141x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1143x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1143x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1146x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1146x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1148x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1148x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1149x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1149x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x114x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x114x1x1x3x1x768x438x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1152x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1152x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1153x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1153x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1155x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1155x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1157x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1157x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1158x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x1158x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x115x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x115x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1162x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1162x1x1x3x1x768x43x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1164x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1164x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1166x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1166x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1167x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1167x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1168x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1168x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1172x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1172x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1173x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1173x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1174x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1174x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1176x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1176x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1179x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1179x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1180x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1180x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1183x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1183x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1185x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1185x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1186x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1186x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x118x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x118x1x1x3x1x768x423x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1190x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1190x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1192x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1192x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1194x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1194x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1198x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1198x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1199x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1199x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1201x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1201x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1202x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1202x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1206x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1206x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1207x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1207x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1210x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1210x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1211x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1211x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1216x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1216x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1218x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1218x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x121x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x121x1x1x3x1x768x413x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1221x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1225x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1225x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1227x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1227x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1232x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1232x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1234x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1234x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1236x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1236x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1238x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1238x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1241x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1241x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1244x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1244x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1249x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1249x1x1x3x1x768x40x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1254x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1254x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1256x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1256x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1259x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1259x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x125x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x125x1x1x3x1x768x400x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1260x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1260x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1264x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1264x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x126x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x126x1x1x3x1x768x396x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1271x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1271x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1272x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1272x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1274x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1274x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1278x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1278x1x1x3x1x768x39x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1283x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1283x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1285x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1285x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1286x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1286x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1293x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1293x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1296x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1296x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1297x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1297x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1298x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1298x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1299x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1299x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1304x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1304x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1308x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1308x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x130x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x130x1x1x3x1x768x384x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1312x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1312x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1315x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1315x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1319x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1319x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1320x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1320x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1323x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1323x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1327x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1327x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1331x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1331x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1334x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1334x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x133x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x133x1x1x3x1x768x375x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1340x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1340x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1341x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1341x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1349x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1349x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x134x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x134x1x1x3x1x768x373x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1350x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1350x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1352x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1352x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1353x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1353x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1354x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1354x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1361x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1361x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1363x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1363x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1364x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1364x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1371x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1371x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1372x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1372x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1377x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1377x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1379x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1379x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x137x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x137x1x1x3x1x768x364x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1384x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1384x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1385x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1385x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1394x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1394x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1399x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1399x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1400x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1400x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1408x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1408x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1409x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1409x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x140x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x140x1x1x3x1x768x357x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1413x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1413x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1417x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1417x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1419x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1419x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1422x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1422x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1426x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1426x1x1x3x1x768x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x142x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x142x1x1x3x1x768x352x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1431x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1431x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1432x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1432x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1433x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1433x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1440x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1440x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1443x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1443x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1444x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1444x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1451x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1451x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1452x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1452x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1454x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1454x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1456x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1456x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1463x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1463x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1468x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1468x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1470x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1470x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1473x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1475x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1479x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1487x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1488x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1488x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x148x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x148x1x1x3x1x768x337x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1496x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1496x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x149x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x149x1x1x3x1x768x335x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1500x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1500x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1502x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1502x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1507x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1507x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1509x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1509x1x1x3x1x768x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x150x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x150x1x1x3x1x768x333x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1516x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1516x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1521x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1521x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1523x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1523x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1527x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1527x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1533x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1533x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1535x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1535x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1539x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1539x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1543x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1543x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1548x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1548x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x154x1x1x3x1x768x324x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1551x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1551x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1552x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x1552x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1555x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1555x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x155x1x1x3x1x768x322x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1562x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1562x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1569x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1569x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1570x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1570x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1573x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1573x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1586x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1586x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1587x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1587x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1594x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1594x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x159x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x159x1x1x3x1x768x314x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1603x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1603x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1606x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1606x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1607x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1607x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1608x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1608x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x160x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x160x1x1x3x1x768x312x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1610x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1610x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1625x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1625x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1626x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1626x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1628x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1628x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1629x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1629x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1636x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1636x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1646x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1646x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1647x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1647x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x164x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x164x1x1x3x1x768x304x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1651x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1651x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1654x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1654x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1660x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1660x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1662x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1662x1x1x3x1x768x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x166x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x166x1x1x3x1x768x301x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1675x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1675x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1676x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1676x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1679x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1679x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1680x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1680x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1698x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1698x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x169x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x169x1x1x3x1x768x295x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1703x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1703x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1708x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1708x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x170x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x170x1x1x3x1x768x294x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1722x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1722x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1724x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1724x1x1x3x1x768x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1728x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1728x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x172x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x172x1x1x3x1x768x290x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1733x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1733x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1734x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1734x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1748x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1748x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x174x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x174x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1759x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1759x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1760x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1760x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x176x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x176x1x1x3x1x768x284x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1770x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1770x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1782x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1782x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1784x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1784x1x1x3x1x768x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1786x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1786x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x178x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x178x1x1x3x1x768x280x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1791x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1791x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1806x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1806x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x180x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x180x1x1x3x1x768x277x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x181x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x181x1x1x3x1x768x276x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1821x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1821x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1824x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1824x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x182x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x182x1x1x3x1x768x274x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1833x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1833x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1840x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1840x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1848x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1848x1x1x3x1x768x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x184x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x184x1x1x3x1x768x271x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1852x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1852x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1869x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1869x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x186x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x186x1x1x3x1x768x268x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1870x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1870x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1881x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1881x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1883x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1883x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x188x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x188x1x1x3x1x768x265x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1902x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1902x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x190x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x190x1x1x3x1x768x263x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1916x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1916x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1918x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1918x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1928x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x1928x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x192x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x192x1x1x3x1x768x260x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1942x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1942x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x194x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x194x1x1x3x1x768x257x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1957x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1957x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x1960x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1960x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x196x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x196x1x1x3x1x768x255x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1979x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1981x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1981x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x198x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x198x1x1x3x1x768x252x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1993x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1993x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1997x1x1x3x1x768x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x199x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x199x1x1x3x1x768x251x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1x1x1x1x1x1280x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x1x1x1x1x1x1920x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x1x1x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x1x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2008x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2008x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x200x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x200x1x1x3x1x768x250x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2017x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2017x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2025x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2025x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x202x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x202x1x1x3x1x768x247x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2051x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2051x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2053x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2053x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2056x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2056x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2057x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2057x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x205x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x205x1x1x3x1x768x243x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x206x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x206x1x1x3x1x768x242x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2074x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2074x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x207x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x207x1x1x3x1x768x241x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2082x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2082x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x208x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x208x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2098x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2098x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2102x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2102x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2105x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2105x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x210x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x210x1x1x3x1x768x238x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2127x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2127x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x212x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x212x1x1x3x1x768x235x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2134x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2134x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2146x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2146x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x214x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x214x1x1x3x1x768x233x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2152x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2152x1x1x3x1x768x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x216x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x216x1x1x3x1x768x231x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x217x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x217x1x1x3x1x768x230x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2182x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2182x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x218x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x218x1x1x3x1x768x229x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2190x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2190x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x219x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x219x1x1x3x1x768x228x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2205x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2205x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x220x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x220x1x1x3x1x768x227x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x222x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x222x1x1x3x1x768x225x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2233x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2233x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x224x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x224x1x1x3x1x768x223x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2251x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2251x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2257x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2257x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2260x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2260x1x1x3x1x768x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x226x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x226x1x1x3x1x768x221x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2278x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x2278x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2282x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2282x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x228x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x228x1x1x3x1x768x219x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x229x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x229x1x1x3x1x768x218x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x230x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x230x1x1x3x1x768x217x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2315x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2315x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2318x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2318x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x232x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x232x1x1x3x1x768x215x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x233x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x233x1x1x3x1x768x214x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2346x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x2346x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x234x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x234x1x1x3x1x768x213x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x236x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x236x1x1x3x1x768x211x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2372x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2372x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2388x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x238x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x238x1x1x3x1x768x210x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x239x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x239x1x1x3x1x768x209x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x240x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x240x1x1x3x1x768x208x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2417x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2422x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x242x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x242x1x1x3x1x768x206x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x244x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x244x1x1x3x1x768x204x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2467x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x246x1x1x3x1x768x203x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x248x1x1x3x1x768x201x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2492x1x1x3x1x768x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x250x1x1x3x1x768x200x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x251x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x251x1x1x3x1x768x199x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2542x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2542x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2548x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2548x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x254x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x254x1x1x3x1x768x196x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2566x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2566x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2568x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2568x1x1x3x1x768x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x256x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x256x1x1x3x1x768x195x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x257x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x257x1x1x3x1x768x194x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x258x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x258x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x259x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x259x1x1x3x1x768x193x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x260x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x260x1x1x3x1x768x192x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x262x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x262x1x1x3x1x768x190x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x264x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x264x1x1x3x1x768x189x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x266x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x266x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x267x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x267x1x1x3x1x768x187x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x268x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x268x1x1x3x1x768x186x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x269x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x269x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x270x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x270x1x1x3x1x768x185x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x271x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x271x1x1x3x1x768x184x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2727x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x2727x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2729x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x2729x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x272x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x272x1x1x3x1x768x183x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2745x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2745x1x1x3x1x768x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x274x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x274x1x1x3x1x768x182x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x275x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x275x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x276x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x276x1x1x3x1x768x181x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x277x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x277x1x1x3x1x768x180x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x278x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x278x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x279x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x279x1x1x3x1x768x179x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x280x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x280x1x1x3x1x768x178x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x282x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x282x1x1x3x1x768x177x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x283x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x283x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x284x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x284x1x1x3x1x768x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x286x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x286x1x1x3x1x768x174x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x288x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x288x1x1x3x1x768x173x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x290x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x290x1x1x3x1x768x172x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x291x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x291x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x292x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x292x1x1x3x1x768x171x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x294x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x294x1x1x3x1x768x170x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x295x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x295x1x1x3x1x768x169x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x296x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x296x1x1x3x1x768x168x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2978x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2978x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x298x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x298x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2994x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2994x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2997x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2997x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x299x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x299x1x1x3x1x768x167x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x3000x1x1x3x1x1280x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x1x3000x1x1x3x1x1280x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x3000x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x3000x1x1x3x1x768x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x300x1x1x3x1x768x166x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x303x1x1x3x1x768x165x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x304x1x1x3x1x768x164x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x305x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x306x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x308x1x1x3x1x768x162x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x309x1x1x3x1x768x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x310x1x1x3x1x768x161x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x312x1x1x3x1x768x160x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x314x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x314x1x1x3x1x768x159x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x315x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x315x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x316x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x316x1x1x3x1x768x158x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x317x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x317x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x318x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x318x1x1x3x1x768x157x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x319x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x319x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x320x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x320x1x1x3x1x768x156x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x322x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x322x1x1x3x1x768x155x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x323x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x323x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x324x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x324x1x1x3x1x768x154x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x325x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x325x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x326x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x326x1x1x3x1x768x153x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x328x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x328x1x1x3x1x768x152x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x330x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x330x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x331x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x331x1x1x3x1x768x151x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x332x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x332x1x1x3x1x768x150x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x334x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x334x1x1x3x1x768x149x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x336x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x336x1x1x3x1x768x148x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x338x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x338x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x339x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x339x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x340x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x340x1x1x3x1x768x147x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x341x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x341x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x342x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x342x1x1x3x1x768x146x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x343x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x343x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x344x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x344x1x1x3x1x768x145x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x345x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x345x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x346x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x346x1x1x3x1x768x144x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x348x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x348x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x349x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x349x1x1x3x1x768x143x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x350x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x350x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x351x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x351x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x352x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x352x1x1x3x1x768x142x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x354x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x354x1x1x3x1x768x141x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x355x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x355x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x356x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x356x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x357x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x357x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x358x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x358x1x1x3x1x768x139x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x360x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x360x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x362x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x362x1x1x3x1x768x138x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x364x1x1x3x1x768x137x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x366x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x367x1x1x3x1x768x136x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x368x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x369x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x370x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x372x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x373x1x1x3x1x768x134x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x374x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x375x1x1x3x1x768x133x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x376x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x377x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x378x1x1x3x1x768x132x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x380x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x381x1x1x3x1x768x131x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x382x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x383x1x1x3x1x768x130x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x385x1x1x3x1x768x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x386x1x1x3x1x768x129x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x388x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x388x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x389x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x389x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x390x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x390x1x1x3x1x768x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x391x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x391x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x392x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x392x1x1x3x1x768x127x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x394x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x394x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x395x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x395x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x396x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x396x1x1x3x1x768x126x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x397x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x397x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x398x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x398x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x400x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x400x1x1x3x1x768x125x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x402x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x402x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x403x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x403x1x1x3x1x768x124x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x404x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x404x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x406x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x406x1x1x3x1x768x123x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x408x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x408x1x1x3x1x768x122x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x410x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x410x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x412x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x412x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x413x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x413x1x1x3x1x768x121x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x414x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x414x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x416x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x416x1x1x3x1x768x120x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x417x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x417x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x418x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x418x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x419x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x419x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x420x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x420x1x1x3x1x768x119x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x421x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x421x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x423x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x423x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x425x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x425x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x426x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x426x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x427x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x427x1x1x3x1x768x117x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x428x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x428x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x430x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x430x1x1x3x1x768x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x432x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x1x432x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x433x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x433x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x434x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x434x1x1x3x1x768x115x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x435x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x435x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x436x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x436x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x437x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x437x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x438x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x438x1x1x3x1x768x114x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x440x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x440x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x441x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x441x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x442x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x442x1x1x3x1x768x113x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x444x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x444x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x445x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x445x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x446x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x446x1x1x3x1x768x112x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x447x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x447x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x448x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x448x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x450x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x450x1x1x3x1x768x111x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x452x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x452x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x453x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x453x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x454x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x454x1x1x3x1x768x110x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x455x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x456x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x458x1x1x3x1x768x109x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x459x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x460x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x462x1x1x3x1x768x108x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x463x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x464x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x465x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x466x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x467x1x1x3x1x768x107x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x468x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x470x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x471x1x1x3x1x768x106x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x472x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x474x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x476x1x1x3x1x768x105x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x477x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x478x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x479x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x480x1x1x3x1x768x104x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x482x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x484x1x1x3x1x768x103x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x486x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x488x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x490x1x1x3x1x768x102x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x492x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x493x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x494x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x495x1x1x3x1x768x101x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x496x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x497x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x498x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x499x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x500x1x1x3x1x768x100x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x501x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x502x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x503x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x504x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x505x1x1x3x1x768x99x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x506x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x507x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x508x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x509x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x510x1x1x3x1x768x98x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x511x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x512x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x513x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x514x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x515x1x1x3x1x768x97x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x516x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x517x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x518x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x519x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x51x1x1x3x1x768x163x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x51x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x1x520x1x1x3x1x768x96x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x521x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x522x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x523x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x524x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x525x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x526x1x1x3x1x768x95x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x527x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x528x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x529x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x530x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x531x1x1x3x1x768x94x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x532x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x533x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x535x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x536x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x537x1x1x3x1x768x93x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x538x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x539x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x540x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x541x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x542x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x543x1x1x3x1x768x92x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x544x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x545x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x546x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x547x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x548x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x549x1x1x3x1x768x91x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x550x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x551x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x552x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x553x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x554x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x555x1x1x3x1x768x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x556x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x557x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x558x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x559x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x560x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x561x1x1x3x1x768x89x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x562x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x563x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x564x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x565x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x566x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x567x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x568x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x569x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x570x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x571x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x572x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x573x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x574x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x575x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x576x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x577x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x578x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x579x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x580x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x581x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x582x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x583x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x584x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x585x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x586x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x587x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x588x1x1x3x1x768x85x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x589x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x590x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x591x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x592x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x593x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x594x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x595x1x1x3x1x768x84x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x596x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x597x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x598x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x600x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x601x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x602x1x1x3x1x768x83x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x603x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x604x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x606x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x607x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x608x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x609x1x1x3x1x768x82x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x610x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x611x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x612x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x613x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x614x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x615x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x616x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x617x1x1x3x1x768x81x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x618x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x620x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x621x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x622x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x623x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x624x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x625x1x1x3x1x768x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x626x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x627x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x628x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x629x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x62x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x62x1x1x3x1x768x462x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x630x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x631x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x632x1x1x3x1x768x79x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x634x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x636x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x637x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x638x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x639x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x640x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x641x1x1x3x1x768x78x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x642x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x643x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x644x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x645x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x646x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x647x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x648x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x649x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x650x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x651x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x652x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x653x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x654x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x656x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x657x1x1x3x1x768x76x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x658x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x659x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x65x1x1x3x1x768x517x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x660x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x661x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x662x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x663x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x664x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x665x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x666x1x1x3x1x768x75x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x667x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x668x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x669x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x670x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x671x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x672x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x673x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x674x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x675x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x676x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x677x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x678x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x679x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x680x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x681x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x682x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x683x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x684x1x1x3x1x768x73x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x685x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x686x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x687x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x688x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x689x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x690x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x691x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x692x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x693x1x1x3x1x768x72x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x695x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x697x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x698x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x699x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x700x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x701x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x702x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x703x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x704x1x1x3x1x768x71x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x705x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x706x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x708x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x709x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x710x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x711x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x713x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x714x1x1x3x1x768x70x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x715x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x716x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x717x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x718x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x719x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x720x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x721x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x722x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x723x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x724x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x725x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x727x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x729x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x730x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x731x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x732x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x733x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x734x1x1x3x1x768x68x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x736x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x737x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x738x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x739x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x740x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x742x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x743x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x744x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x745x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x746x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x747x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x748x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x749x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x74x1x1x3x1x768x675x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x750x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x751x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x752x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x753x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x754x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x755x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x756x1x1x3x1x768x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x758x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x759x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x760x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x761x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x762x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x764x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x765x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x767x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x768x1x1x3x1x768x65x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x76x1x1x3x1x768x657x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x770x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x772x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x773x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x775x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x776x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x777x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x778x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x779x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x77x1x1x3x1x768x649x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x780x1x1x3x1x768x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x782x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x783x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x785x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x786x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x787x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x789x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x78x1x1x3x1x768x641x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x790x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x792x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x793x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x794x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x794x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x795x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x795x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x796x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x796x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x797x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x797x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x798x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x798x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x79x1x1x3x1x768x632x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x800x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x800x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x801x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x801x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x802x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x802x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x804x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x804x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x805x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x805x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x806x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x806x1x1x3x1x768x62x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x807x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x807x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x808x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x808x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x810x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x810x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x811x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x811x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x812x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x812x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x813x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x813x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x814x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x814x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x815x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x815x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x816x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x816x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x818x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x818x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x819x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x819x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x820x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x822x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x823x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x824x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x825x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x826x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x827x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x828x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x829x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x830x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x831x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x832x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x833x1x1x3x1x768x60x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x835x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x836x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x837x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x838x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x839x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x840x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x841x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x842x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x843x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x844x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x845x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x846x1x1x3x1x768x59x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x848x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x848x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x849x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x84x1x1x3x1x768x595x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x850x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x851x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x852x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x853x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x854x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x856x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x857x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x858x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x859x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x860x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x861x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x862x1x1x3x1x768x58x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x863x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x863x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x865x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x865x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x866x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x866x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x869x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x869x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x870x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x870x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x872x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x872x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x873x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x873x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x875x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x875x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x876x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x876x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x879x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x879x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x880x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x880x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x882x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x882x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x883x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x883x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x884x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x884x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x886x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x886x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x887x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x887x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x888x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x888x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x889x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x889x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x891x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x891x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x892x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x892x1x1x3x1x768x56x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x893x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x893x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x894x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x894x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x895x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x895x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x896x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x896x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x898x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x898x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x899x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x899x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x89x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x89x1x1x3x1x768x561x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x901x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x901x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x902x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x902x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x904x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x904x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x905x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x905x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x906x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x906x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x908x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x908x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x909x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x909x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x912x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x912x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x913x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x913x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x914x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x914x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x915x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x915x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x916x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x916x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x918x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x918x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x919x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x919x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x920x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x920x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x923x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x923x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x924x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x924x1x1x3x1x768x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x926x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x926x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x928x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x928x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x929x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x929x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x92x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x92x1x1x3x1x768x543x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x931x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x931x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x932x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x932x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x933x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x933x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x934x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x934x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x935x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x935x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x938x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x938x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x939x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x939x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x941x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x941x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x943x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x943x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x944x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x946x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x947x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x948x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x949x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x950x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x952x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x953x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x954x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x955x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x957x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x959x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x960x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x961x1x1x3x1x768x52x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x963x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x963x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x965x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x965x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x966x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x966x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x967x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x967x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x969x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x969x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x96x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x96x1x1x3x1x768x520x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x972x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x972x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x973x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x973x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x974x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x974x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x976x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x976x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x978x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x978x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x980x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x980x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x982x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x1x982x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x986x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x986x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x987x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x987x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x989x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x989x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x991x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x991x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x993x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x993x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x994x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x1x994x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x996x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x996x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x997x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x997x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x998x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x998x1x1x3x1x768x50x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x24x24x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x1x1x1x171x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x80x256x256x1x1x1x1x240x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x256x256x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x256x256x1x2x2x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x256x256x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x256x256x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x5xNCHWxFP16xF=ConvBinWinogradRxSf2x3:101;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x256x256x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x256x256x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x5x5x1x80x1x2x2x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x5x5x1x80x4x2x2x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x7x7x1x80x1x3x3x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x256x256x1x7x7x1x80x1x3x3x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x259x259x1x5x5x1x80x1x0x0x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x261x261x1x7x7x1x80x4x0x0x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x28x28x1x1x1x1x120x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x28x28x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x102x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x103x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x105x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x106x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x107x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x108x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x109x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x110x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x111x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x113x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x115x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x116x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x117x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x118x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x119x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x80x28x28x1x1x1x1x256x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x121x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x122x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x123x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x124x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x125x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x126x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x129x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x130x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x131x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x133x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x134x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x135x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x137x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x138x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x139x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x80x28x28x1x1x1x1x256x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x140x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x141x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x142x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x143x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x145x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x146x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x147x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x148x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x149x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x150x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x153x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x154x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x155x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x157x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x158x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x159x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x161x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x162x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x163x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x164x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x165x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x166x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x167x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x169x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x170x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x172x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x173x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x174x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x175x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x175x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x178x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x179x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x180x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x181x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x182x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x183x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x185x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x186x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x187x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x188x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x188x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x189x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x190x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x191x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x191x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x193x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x194x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x195x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x196x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x197x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x197x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x198x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x198x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x199x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x28x28x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x201x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x202x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x202x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x203x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x204x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x205x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x205x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x206x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x207x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x207x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x209x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,51;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x80x28x28x1x1x1x1x256x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x210x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x211x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x212x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x212x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x213x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x214x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x215x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x217x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x218x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x219x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x220x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x220x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x221x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x222x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x222x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x223x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x225x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x226x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x226x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x227x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x228x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x229x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x230x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x231x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x233x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x234x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x234x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x236x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x236x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x237x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x237x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x238x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x241x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x242x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x244x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x244x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x245x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x245x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x246x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x246x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x247x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x249x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x249x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,256,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,33[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x250x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x254x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x254x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x255x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x80x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x80x28x28x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 2, 1, 1>+1
2x80x28x28x1x1x1x1x256x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x80x28x28x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x41x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x44x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x47x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x80x28x28x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x80x28x28x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x58x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x59x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x60x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x61x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x62x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x63x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x65x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x66x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x67x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x68x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x69x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x70x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x71x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x73x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x75x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x76x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 2, 4, 4, 4, 1, 1>+1
2x80x28x28x1x1x1x1x256x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x28x28x1x1x1x1x256x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x78x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x79x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x81x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x83x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x85x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x87x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x89x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x256x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x90x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x91x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x92x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[4];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x94x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x95x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x97x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x98x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x28x28x1x1x1x1x256x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x99x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[6];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x28x28x1x1x1x1x256x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x28x28x1x1x1x1x256x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:84;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x80x28x28x1x1x1x1x52x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x28x28x1x3x3x1x160x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x28x28x1x3x3x1x640x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x28x28x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x28x28x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x28x28x1x5x5x1x80x1x2x2x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x29x29x1x3x3x1x80x1x0x0x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x32x32x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x32x32x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x32x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x32x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x32x32x1x3x3x1x80x1x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x4x4x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x512x512x1x2x2x1x160x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x2x2x1x160x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x512x512x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x512x512x1x5x5x1x80x1x2x2x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x512x512x1x5x5x1x80x1x2x2x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x512x512x1x7x7x1x160x4x3x3x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x80x56x56x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x56x56x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x56x56x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x3x3x1x120x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x56x56x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x80x56x56x1x3x3x1x320x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x80x56x56x1x3x3x1x80x1x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x56x56x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x3x3x1x80x4x1x1x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x5x5x1x80x1x2x2x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x5x5x1x80x4x2x2x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x56x56x1x7x7x1x160x4x3x3x0x2x2x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x80x64x64x1x15x15x1x3x8x7x7x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x80x64x64x1x1x1x1x200x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x64x64x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x64x64x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x64x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x64x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x64x64x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x80x64x64x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x80x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x80x71x71x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,0;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,26;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x80x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x80x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x80x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x80x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x80x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x80x73x73x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,2,1,8,1,32,116;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x80x73x73x1x1x1x1x64x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,200;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x80x73x73x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x80x73x73x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x73x73x1x3x3x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x73x73x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x80x73x73x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x73x73x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x80x73x73x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x73x73x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x73x73x1x3x3x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Default, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,79;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, OddC, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x192x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x73x73x1x3x3x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x80x73x73x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,91;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x80x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x80x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x80x7x7x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x80x7x7x1x1x1x1x184x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x80x7x7x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x80x7x7x1x3x3x1x80x4x1x1x0x1x1x0x1x1x0x0x80xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x80x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x816x128x128x1x3x3x1x816x1x1x1x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x128x128x1x3x3x1x816x4x1x1x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x128x128x1x5x5x1x816x1x2x2x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x131x131x1x5x5x1x816x4x0x0x0x2x2x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x14x14x1x1x1x1x136x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 192, 16, Filter1x1Pad0, 32, 32, 2, 3, 4, 4, 4, 1, 1, 1>
2x816x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x816x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x816x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x816x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x816x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x816x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x816x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x816x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x816x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x816x15x15x1x3x3x1x816x4x0x0x0x2x2x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x17x17x1x5x5x1x816x4x0x0x0x2x2x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x19x19x1x1x1x1x136x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x816x19x19x1x5x5x1x816x4x2x2x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x23x23x1x5x5x1x816x4x0x0x0x2x2x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x64x64x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x816x64x64x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x816x64x64x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x816x64x64x1x3x3x1x816x1x1x1x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x816x64x64x1x5x5x1x816x1x2x2x0x1x1x0x1x1x0x0x816xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x818x128x128x1x1x1x1x253x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x818x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x818x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x818x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x818x14x14x1x1x1x1x492x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x818x64x64x1x1x1x1x2022x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x818x64x64x1x1x1x1x2022x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
2x818x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8192x128x128x1x3x3x1x8192x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x8192x14x14x1x3x3x1x8192x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x8192x64x64x1x3x3x1x8192x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x81x14x14x1x5x5x1x81x1x2x2x0x1x1x0x1x1x0x0x81xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x81x14x14x1x7x7x1x81x1x3x3x0x1x1x0x1x1x0x0x81xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x81x1x1x1x1x1x1x972x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x81x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x81x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x81x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x81x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x81x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x81x28x28x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x81x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x81x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x81x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,205[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>+1
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,256,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,4,1,4,1,64,111[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x800x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x81x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>+1
2x81x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x81x28x28x1x5x5x1x81x4x2x2x0x1x1x0x1x1x0x0x81xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x81x512x512x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x81x7x7x1x7x7x1x81x1x3x3x0x1x1x0x1x1x0x0x81xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x824x32x32x1x1x1x1x4944x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x824x64x64x1x1x1x1x4944x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x8256x64x64x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,109[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x8256x64x64x1x3x3x1x8256x1x1x1x0x1x1x0x1x1x0x0x8256xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x8256x7x7x1x1x1x1x1376x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x828x128x128x1x1x1x1x152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x828x14x14x1x1x1x1x152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x82x1x1x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x82x56x56x1x1x1x1x492x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x128x128x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x128x128x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x832x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x832x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x256x256x1x1x1x1x1088x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x256x256x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x28x28x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x5x5x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x5x5x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x832x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x832x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x64x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x64x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x64x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x64x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x64x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x64x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x64x64x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x832x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+4
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x832x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[4];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:104;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:106;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x832x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,222[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x832x7x7x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,2,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42[2];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x832x7x7x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+16
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:166;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x832x7x7x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x832x7x7x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x3x3x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, Default, 32, 32, 1, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x3x3x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x832x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x832x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, OddC, 32, 32, 1, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,257[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x832x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x832x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1]
2x832x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,244[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x83x128x128x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x83x256x256x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x83x256x256x1x3x3x1x83x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x83x28x28x1x1x1x1x166x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x83x28x28x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x83x515x515x1x5x5x1x83x1x0x0x0x2x2x0x1x1x0x0x83xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x83x56x56x1x3x3x1x166x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x83x56x56x1x3x3x1x83x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x83x59x59x1x5x5x1x83x4x0x0x0x2x2x0x1x1x0x0x83xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x840x64x64x1x1x1x1x151x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x840x7x7x1x1x1x1x151x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x840x7x7x1x3x3x1x840x1x1x1x0x1x1x0x1x1x0x0x840xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x84x128x128x1x7x7x1x84x1x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x14x14x1x1x1x1x504x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x84x1x1x1x1x1x1x336x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x84x256x256x1x5x5x1x84x1x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x256x256x1x7x7x1x84x4x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x259x259x1x5x5x1x84x1x0x0x0x2x2x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x84x28x28x1x5x5x1x84x1x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x84x28x28x1x5x5x1x84x4x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x84x28x28x1x7x7x1x84x4x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x84x42x42x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x84x42x42x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,18;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>+1
2x84x42x42x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,19;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x84x42x42x1x1x1x1x84x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x84x42x42x1x3x3x1x84x64x1x1x0x1x1x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x84x42x42x1x3x3x1x84x64x1x1x0x1x1x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x84x42x42x1x3x3x1x84x64x1x1x0x1x1x0x1x1x0x0x84xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x84x42x42x1x5x5x1x84x64x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x84x42x42x1x5x5x1x84x64x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x42x42x1x5x5x1x84x64x2x2x0x1x1x0x1x1x0x0x84xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x84x42x42x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x84x42x42x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x84x42x42x1x7x7x1x84x64x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x84x42x42x1x7x7x1x84x64x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x42x42x1x7x7x1x84x64x3x3x0x1x1x0x1x1x0x0x84xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x84x42x42x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x84x42x42x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x84x44x44x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x84x44x44x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x84x45x45x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xB=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x84x45x45x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x84x515x515x1x5x5x1x84x4x0x0x0x2x2x0x1x1x0x0x84xNCHWxFP16xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 256, 32, Default, 32, 32, 2, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x84x83x83x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x84x83x83x1x1x1x1x168x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x84x83x83x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,33;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x84x83x83x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x83x83x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 128, 128, 64, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x84x84x84x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x84x84x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x84x87x87x1x5x5x1x84x64x2x2x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x84x89x89x1x7x7x1x84x64x3x3x0x2x2x0x1x1x0x0x84xNCHWxFP32xF=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x852x128x128x1x1x1x1x159x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x852x14x14x1x1x1x1x159x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x85x128x128x1x1x1x1x171x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x128x128x1x1x1x1x254x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x128x128x1x1x1x1x254x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x128x128x1x1x1x1x274x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x14x14x1x1x1x1x274x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x28x28x1x1x1x1x171x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x28x28x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x85x28x28x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x85x28x28x1x5x5x1x85x1x2x2x0x1x1x0x1x1x0x0x85xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x28x28x1x5x5x1x85x4x2x2x0x1x1x0x1x1x0x0x85xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x85x56x56x1x3x3x1x37x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x85x64x64x1x1x1x1x292x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x864x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x128x128x1x1x1x1x167x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x864x128x128x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x864x128x128x1x1x1x1x864x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x864x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+1
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,52[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[9];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:116;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+16
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x864x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:94;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x864x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x1x1x1x416x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x14x14x1x3x3x1x864x4x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x14x14x1x5x5x1x864x1x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x1x1x1x1x1x1x216x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x1x1x1x1x1x1x36x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,1,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,95[1];ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x256x256x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x864x256x256x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x864x256x256x1x3x3x1x864x1x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x64x64x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x64x64x1x1x1x1x167x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x864x64x64x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x64x64x1x1x1x1x864x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x64x64x1x3x3x1x864x4x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x64x64x1x7x7x1x864x4x3x3x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x864x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:114;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x864x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146;ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x864x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x864x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x864x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x864x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,282[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x144x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:165;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x144x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x864x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x864x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x864x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x864x7x7x1x1x1x1x864x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x16x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x32x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x3x3x1x864x64x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+8
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x864x7x7x1x5x5x1x864x16x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+-1
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x5x5x1x864x32x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+-1
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x864x7x7x1x5x5x1x864x64x2x2x0x1x1x0x1x1x0x0x864xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x864x7x7x1x7x7x1x864x4x3x3x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x872x128x128x1x5x5x1x872x4x2x2x0x2x2x0x1x1x0x0x872xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x872x64x64x1x1x1x1x104x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x872x64x64x1x1x1x1x72x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x872x7x7x1x5x1x1x872x4x2x0x0x1x1x0x1x1x0x0x872xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x87x128x128x1x1x1x1x171x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x87x1x1x1x1x1x1x1044x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x87x28x28x1x1x1x1x171x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x888x64x64x1x3x3x1x888x1x1x1x0x1x1x0x1x1x0x0x37xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x888x7x7x1x3x3x1x888x1x1x1x0x1x1x0x1x1x0x0x37xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x88x112x112x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:96;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x112x112x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x112x112x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x88x112x112x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x112x112x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x88x113x113x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x113x113x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x113x113x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x88x113x113x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x113x113x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x88x128x128x1x1x1x1x124x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x88x128x128x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x128x128x1x3x3x1x352x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x88x128x128x1x3x3x1x88x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x88x128x128x1x3x3x1x88x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x88x14x14x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x88x14x14x1x1x1x1x268x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x88x14x14x1x2x2x1x168x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x14x14x1x3x3x1x352x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x88x14x14x1x3x3x1x88x4x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x14x14x1x5x5x1x88x1x2x2x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x17x17x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x1x1x1x1x1x1x1008x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x88x223x223x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x224x224x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x224x224x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x224x224x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x225x225x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x225x225x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x225x225x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x256x256x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x88x256x256x1x1x1x1x528x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x256x256x1x3x3x1x88x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x88x256x256x1x3x3x1x88x1x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x256x256x1x3x3x1x88x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x27x27x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x88x28x28x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,1,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,176[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,1,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,11[1];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,2,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[2];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x1x1x1x88x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x88x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x88x28x28x1x1x1x1x88x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[1];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x88x28x28x1x1x1x1x88x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,1,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x88x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:73;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x88x28x28x1x1x1x1x88x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,273;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x88x28x28x1x1x1x1x88x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,16;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x88x28x28x1x1x1x1x88x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x28x28x1x1x1x1x88x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x88x28x28x1x1x1x1x88x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x88x28x28x1x1x1x1x88x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x88x28x28x1x3x3x1x88x10x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x10x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x10x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x10x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x10x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x10x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x10x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x10x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x11x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x11x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x11x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x11x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x11x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x11x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x11x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x11x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x128x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x88x28x28x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x16x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x16x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x16x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x16x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x16x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x3x3x1x88x1x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x20x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x20x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x20x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x20x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x20x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x20x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x20x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x20x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x32x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x88x28x28x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+-1
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x64x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xB=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 8>+64
2x88x28x28x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x88x28x28x1x3x3x1x88x8x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x8x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x28x28x1x3x3x1x88x8x1x1x0x1x1x0x1x1x0x0x88xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x28x28x1x3x3x1x88x8x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x88x28x28x1x3x3x1x88x8x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x88x32x32x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x512x512x1x3x3x1x88x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x55x55x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x55x55x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x55x55x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x55x55x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x55x55x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x55x55x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,34;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x88x56x56x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,10;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x56x56x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x88x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x88x56x56x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x128x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x128x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x22x1x1x0x2x2x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x32x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x32x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x4x1x1x0x1x1x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x56x56x1x3x3x1x88x4x1x1x0x2x2x0x1x1x0x0x11xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x88x56x56x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x64x0x0x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x64x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x56x56x1x3x3x1x88x8x1x1x0x2x2x0x1x1x0x0x88xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x88x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x88x64x64x1x1x1x1x528x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x88x64x64x1x5x5x1x88x1x2x2x0x2x2x0x1x1x0x0x88xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x891x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x891x64x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x894x128x128x1x3x3x1x894x1x1x1x0x1x1x0x1x1x0x0x894xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x894x256x256x1x1x1x1x183x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x894x28x28x1x1x1x1x183x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x894x28x28x1x3x3x1x894x4x1x1x0x1x1x0x1x1x0x0x894xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:205;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:204;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:219;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x181x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x181x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:174;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x118x181x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x118x181x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x181x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:239;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:220;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x118x182x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x118x182x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x118x182x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x118x182x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x118x182x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x118x182x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x118x182x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x128x128x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x2016x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x128x128x1x1x1x1x2240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x672x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x128x128x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x896x128x128x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x128x128x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x128x128x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x128x128x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x128x128x1x5x5x1x896x4x2x2x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[2];ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,2,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[2];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x896x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:171;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:117;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[10];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 128, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 2, 4, 2, 1, 1, 4>+-1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[8];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+4
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+2
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x896x14x14x1x1x1x1x1792x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:234;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,304[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x14x14x1x1x1x1x1792x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:249;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,156[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,256,16,32,32,2,1,1,2,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,16,1,16,1,16,17[5];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:237;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x14x14x1x1x1x1x1792x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,20;ConvBinWinogradRxSf2x3:229;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:228;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+2
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x896x14x14x1x1x1x1x1792x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[4];ConvBinWinogradRxSf2x3:232;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,197[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,145;ConvBinWinogradRxSf2x3:235;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x896x14x14x1x1x1x1x1792x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,0,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,40;ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,256,32,32,32,8,2,2,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,157[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,256,32,32,32,8,2,2,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,8,1,8,1,32,64[1];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,9[7];ConvBinWinogradRxSf2x3:226;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Filter1x1Stride1Pad0, 4, 2, 2, 4, 4, 4, 2, 1, 1, 4>+-1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x896x14x14x1x1x1x1x1792x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[8];ConvBinWinogradRxSf2x3:224;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+1
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:240;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x896x14x14x1x1x1x1x1792x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[9];ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x896x14x14x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[2];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x2240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x2240x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[2];ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x896x14x14x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x14x14x1x5x5x1x896x1x2x2x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x1x1x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[10];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:201;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:233;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x112x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,9,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[9];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x896x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,245[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,6,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[6];ConvBinWinogradRxSf2x3:231;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[3];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,7,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[7];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,209;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,10,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,138[10];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,308[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:218;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x896x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x256x256x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x256x256x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x256x256x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x28x28x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x28x28x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x28x28x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x7xNCHWxFP16xF=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x32x32x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x32x32x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x32x32x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x59x91x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x1x1x1x2016x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x2016x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x2016x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x2016x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x896x59x91x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x896x59x91x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,64,16,16,16,1,1,2,2,1,0,1,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,195[1];ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x896x59x91x1x1x1x1x448x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x896x59x91x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x59x91x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x59x91x1x1x1x1x448x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,265;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,139;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x448x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:112;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+4
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x1x1x1x896x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x10x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x10x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x12x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x12x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x14x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x14x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:95;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x16x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x16x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x896x59x91x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x896x59x91x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x1x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+4
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+4
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x2x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+4
2x896x59x91x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x2x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x896x59x91x1x3x3x1x896x6x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x6x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x7x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x7x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x59x91x1x3x3x1x896x8x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x59x91x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x896x59x91x1x3x3x1x896x8x1x1x0x2x2x0x1x1x0x0x16xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x896x64x64x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x64x64x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x64x64x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x64x64x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x64x64x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x64x64x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x64x64x1x1x1x1x896x1x0x0x0x2x2x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x896x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,89[2];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,3,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,3,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,68[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x896x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:115;ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,2,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,324[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:149;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,3,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,3,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x896x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,4,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x896x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:184;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[2];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:113;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x896x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,2,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,72[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x896x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[2];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,2,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,2,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x896x7x7x1x3x3x1x896x1x1x1x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x896x7x7x1x3x3x1x896x4x1x1x0x1x1x0x1x1x0x0x896xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x8x1024x1024x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1024x1024x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1024x1024x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 64, 8, Default, 32, 32, 4, 1, 1, 1, 8, 1, 1, 1>
2x8x1024x1024x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1024x1024x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x8x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x8x1024x1024x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43
2x8x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x8x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x8x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x1024x1024x1x3x3x1x8x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x8x1025x1025x1x2x2x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 4, 4, 1, 1>+1
2x8x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x8x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,48;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x8x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x8x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x112x112x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x8x112x112x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x112x112x1x1x1x1x4x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x112x112x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x8x112x112x1x3x3x1x16x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x128x128x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x128x128x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x128x128x1x3x3x1x8x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x128x128x1x3x3x1x8x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x128x128x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x14x14x1x3x3x1x8x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x14x14x1x3x3x1x8x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x8x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x8x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x8x1536x1536x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,4,64,32,1,1,1,2,1,0,0,0,1,0,1,1,8,1,1,4,1,32,1,1,1,1,1,4,1,32,10
2x8x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x8x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x8x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x16x16x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x8x16x16x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x18x18x1x3x3x1x8x1x0x0x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x8x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1920x1080x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,8,32,32,2,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,9;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x1x1x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,46;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x8x1x1x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,2,1,1,4,1,64,1,1,1,1,1,4,1,64,34;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+1
2x8x1x1x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x8x1x1x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[6];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x8x1x1x1x1x1x1x2020x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x20x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 2, 1, 1>+8
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,7,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[7];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,8,1,8,1,32,229;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[3];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,311;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x8x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x8x1x1x1x1x1x1x224x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,0,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,208;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[5];ConvBinWinogradRxSf2x3:121;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,8,1,8,1,32,201;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+4
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,183;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[8];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 8, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,192;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x224x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[10];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x8x1x1x1x1x1x1x232x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x8x1x1x1x1x1x1x28x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x1x1x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x8x1x1x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x1x1x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15
2x8x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214
2x8x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118
2x8x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x8x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x8x2048x2048x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44
2x8x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x8x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x8x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29
2x8x256x256x1x1x1x1x16x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 64, 8, Default, 32, 32, 1, 2, 1, 1, 8, 1, 1, 1>
2x8x256x256x1x3x3x1x8x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x256x256x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x8x28x28x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x2x2x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x8x3072x3072x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x8x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x8x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x8x3072x3072x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x8x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204
2x8x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104
2x8x3072x3072x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,0,0,0,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,44
2x8x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,199
2x8x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97
2x8x3072x3072x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x8x32x32x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x49x49x1x1x1x1x8x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x8x49x49x1x1x1x1x8x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x8x4x4x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x8x512x512x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x8x512x512x1x1x1x1x16x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x512x512x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x8x512x512x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x8x512x512x1x3x3x1x8x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x512x512x1x3x3x1x8x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x56x56x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x8x56x56x1x3x3x1x8x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x56x56x1x3x3x1x8x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x64x64x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x64x64x1x1x1x1x8x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,104;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x8x64x64x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,29;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x8x8x8x1x7x7x1x32x27x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,43;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x906x1x1x1x1x1x1x75x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x906x32x32x1x1x1x1x162x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x906x64x64x1x3x3x1x906x4x1x1x0x1x1x0x1x1x0x0x906xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x90x14x14x1x3x3x1x90x4x1x1x0x1x1x0x1x1x0x0x90xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x90x14x14x1x7x7x1x90x1x3x3x0x1x1x0x1x1x0x0x90xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
2x90x256x256x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x90x64x64x1x7x7x1x90x1x3x3x0x1x1x0x1x1x0x0x90xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x90x64x64x1x9x9x1x90x1x4x4x0x1x1x0x1x1x0x0x90xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x912x128x128x1x1x1x1x167x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x912x128x128x1x3x3x1x912x4x1x1x0x1x1x0x1x1x0x0x912xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x912x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x912x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x912x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x912x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x912x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x912x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x912x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x912x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,16,64,32,4,1,1,2,2,0,0,0,0,0,1,8,2,1,1,2,1,128,1,8,1,1,1,2,1,128,80;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x912x14x14x1x3x3x1x912x1x1x1x0x1x1x0x1x1x0x0x912xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x912x1x1x1x1x1x1x76x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x32x32x1x3x3x1x912x1x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x912x64x64x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x912x7x7x1x3x3x1x912x4x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x91x1x1x1x1x1x1x1092x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x924x1x1x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x924x64x64x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x928x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x928x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x928x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:129;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 1, 1, 1>+2
2x928x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:149;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,164[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[5];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:118;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x928x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x928x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x928x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:133;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,1,0,3,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,152[3];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:125;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x928x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:139;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x928x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x92x128x128x1x1x5x1x92x1x0x2x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x128x128x1x3x3x1x92x1x1x1x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x14x14x1x3x3x1x92x1x1x1x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x92x1x1x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x1x1x1x1x1x1x368x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x256x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x256x256x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x92x256x256x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x256x256x1x1x5x1x92x1x0x2x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x256x256x1x1x5x1x92x4x0x2x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x256x256x1x5x5x1x92x1x2x2x0x2x2x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x28x28x1x1x1x1x26x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x92x28x28x1x1x1x1x26x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x92x28x28x1x1x1x1x552x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x28x28x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x28x28x1x3x3x1x92x4x1x1x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x32x32x1x1x1x1x556x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x512x512x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x512x512x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x64x64x1x3x3x1x92x4x1x1x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x92x7x7x1x1x1x1x556x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x7x7x1x1x1x1x556x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x92x7x7x1x3x3x1x92x1x1x1x0x1x1x0x1x1x0x0x92xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x93x128x128x1x1x1x1x236x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 256, 32, Default, 32, 32, 4, 4, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x93x14x14x1x1x1x1x219x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x93x14x14x1x1x1x1x261x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x93x256x256x1x3x3x1x49x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x93x64x64x1x1x1x1x236x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x93x64x64x1x1x1x1x254x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x94x128x128x1x1x1x1x564x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x94x64x64x1x1x1x1x564x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x954x128x128x1x3x3x1x954x1x1x1x0x1x1x0x1x1x0x0x954xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x954x14x14x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x954x14x14x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x954x14x14x1x3x3x1x954x4x1x1x0x1x1x0x1x1x0x0x954xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x95x128x128x1x1x1x1x570x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x95x1x1x1x1x1x1x1140x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x95x1x1x1x1x1x1x1140x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x960x128x128x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x128x128x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x128x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x960x128x128x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x128x128x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x960x128x128x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x128x128x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x960x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,107[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x128x128x1x3x3x1x960x1x1x1x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x128x128x1x3x3x1x960x1x1x1x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[3];ConvBinWinogradRxSf2x3:140;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,25[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,4,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[4];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,24[1];ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x960x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,236[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,179[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x14x14x1x3x3x1x960x1x1x1x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x14x14x1x3x3x1x960x4x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x16x16x1x1x1x1x272x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x16x16x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x16x16x1x1x1x1x640x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x16x16x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x16x16x1x1x1x1x640x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x16x16x1x3x3x1x320x280x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x16x16x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x16x16x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x1x1x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x1x1x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x960x1x1x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x1x1x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+1
2x960x1x1x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,6,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[6];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x960x1x1x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x1x1x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:119;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+1
2x960x1x1x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x24x24x1x5x5x1x960x1x2x2x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x256x256x1x1x1x1x400x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x960x256x256x1x3x3x1x960x1x1x1x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x28x28x1x1x1x1x400x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x960x32x32x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x960x32x32x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x960x32x32x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x32x32x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x1x1x1x320x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x32x32x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x32x32x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x32x32x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:161
2x960x32x32x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,220[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x32x32x1x3x3x1x640x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x32x32x1x5x5x1x960x1x2x2x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x32x32x1x7x7x1x960x1x3x3x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x960x37x37x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x38x38x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x38x38x1x3x3x1x960x4x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x960x3x3x1x1x5x1x960x1x0x2x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x960x48x48x1x3x3x1x640x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,113[1];ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x4x4x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x4x4x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:89;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x176x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,123[1];ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:142;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x320x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x64x64x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,115[1];ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,126[1];ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=TransposedConvBinWinoRxS<3-2>:190
2x960x64x64x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,211[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x64x64x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x64x64x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x3x3x1x640x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x64x64x1x3x3x1x960x1x1x1x0x2x2x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x65x65x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x66x66x1x3x3x1x960x1x0x0x0x2x2x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x67x67x1x5x5x1x960x1x0x0x0x2x2x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x960x73x73x1x3x3x1x960x4x0x0x0x1x1x0x4x4x0x0x960xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,328[1];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x960x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,161[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:198;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,233[1];ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:143;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:120;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x960x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:131;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,1,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,227[1];ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:143;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x960x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:150;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[5];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,173[1];ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:167;ConvBinWinogradRxSf3x2:158;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+8
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,4,1,8,1,8,1,32,1,4,1,1,1,8,1,32,224;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+16
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[8];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,8,16,16,1,1,1,2,2,1,0,6,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,67[6];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+16
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[9];ConvBinWinogradRxSf2x3:207;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[3];ConvBinWinogradRxSf2x3:160;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[5];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,0,0,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,242;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,5,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[5];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,10,0,0,1,4,1,8,1,8,1,32,1,4,1,2,1,8,1,32,101[10];ConvBinWinogradRxSf2x3:223;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,5,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[5];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:169;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[4];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,4,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[4];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:154;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:153;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:210;ConvBinWinogradRxSf3x2:178;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,1,2,1,8,1,32,302;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+4
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,191[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,149[1];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:156;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,60[1];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,320[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,2,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:158;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:161;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+64
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x240x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:192;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+8
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x960x7x7x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,162[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x4x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+32
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:148;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:111;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:110;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x240x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xW=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x960x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,129[1];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,1,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,56[1];ConvBinWinogradRxSf3x2:98;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,181[1];ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x960x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x7x7x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,64,64,16,16,16,1,1,2,2,0,0,0,0,0,1,8,2,1,1,8,1,32,1,8,2,1,1,8,1,32,238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x960x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,1,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,258[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x960x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,1,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,160[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x7x7x1x3x3x1x960x16x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x960x7x7x1x3x3x1x960x16x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x7x7x1x3x3x1x960x16x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+-1
2x960x7x7x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x960x7x7x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x7x7x1x3x3x1x960x32x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+2
2x960x7x7x1x3x3x1x960x64x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x960x7x7x1x3x3x1x960x64x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x960x7x7x1x3x3x1x960x64x1x1x0x1x1x0x1x1x0x0x960xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+4
2x960x7x7x1x5x5x1x960x4x2x2x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x7x7x1x7x7x1x960x4x3x3x0x1x1x0x1x1x0x0x960xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x960x80x80x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x8x8x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:190;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x960x8x8x1x1x1x1x1920x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,24;ConvBinWinogradRxSf2x3:253;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x960x8x8x1x1x1x1x2560x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:246
2x960x8x8x1x1x1x1x2560x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:161
2x960x8x8x1x1x1x1x2560x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,2,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[2];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x960x8x8x1x1x1x1x2560x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:244;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
2x960x8x8x1x1x1x1x2560x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:244
2x960x8x8x1x1x1x1x960x30x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>;TransposedConvBinWinoRxS<3-2>:135
2x960x8x8x1x1x1x1x960x6x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:65
2x960x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,2,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2;TransposedConvBinWinoRxS<3-2>:123
2x960x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>;TransposedConvBinWinoRxS<3-2>:97
2x960x8x8x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2;TransposedConvBinWinoRxS<2-3>:236;TransposedConvBinWinoRxS<3-2>:244
2x960x8x8x1x3x3x1x1920x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x960x8x8x1x3x3x1x1920x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,4,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[4];ConvBinWinogradRxSf2x3:254;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x960x8x8x1x3x3x1x960x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,3,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[3];ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x960x8x8x1x3x3x1x960x30x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,2,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,17[2];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, OddC, 32, 32, 1, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:135
2x960x8x8x1x3x3x1x960x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x8x8x1x3x3x1x960x6x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:67
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,2,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[2];ConvBinWinogradRxSf2x3:242;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,2,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[2];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+8;TransposedConvBinWinoRxS<3-2>:110
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,3,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[3];ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>;TransposedConvBinWinoRxS<3-2>:90
2x960x8x8x1x3x3x1x960x8x1x1x0x1x1x0x1x1x0x0x1xNHWCxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,27[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1;TransposedConvBinWinoRxS<2-3>:249;TransposedConvBinWinoRxS<3-2>:229
2x960x96x96x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x960x96x96x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,75[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x1023x1023x1x1x1x1x42x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,97;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x1024x1024x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x1024x1024x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x1024x1024x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x1024x1024x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209
2x96x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x96x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x96x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x96x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x1024x1024x1x3x3x1x48x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x96x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x96x1024x1024x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x96x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x96x1024x1024x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21
2x96x1024x1024x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x1024x1024x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x1024x1024x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x1024x1024x1x5x5x1x96x1x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x1025x1025x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x1029x1029x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x106x106x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,8,32,32,4,1,1,2,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:119;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x106x106x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:176;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8]
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x106x106x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x109x109x1x7x7x1x3x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x109x109x1x7x7x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x43x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8]
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:183;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x109x109x1x7x7x1x3x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x10x10x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:193;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x111x111x1x1x1x1x42x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x111x111x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x111x111x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x1024x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x111x111x1x7x7x1x3x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x256x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,6,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x111x111x1x7x7x1x3x4x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x512x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8]
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x111x111x1x7x7x1x3x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,125;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4]
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:112;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[9];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:118;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,85[1];ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,110;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,119[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[4]
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,6,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[6];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x112x112x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x112x112x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x112x112x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:139;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x112x112x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x112x112x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x6xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x112x112x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x112x112x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x112x112x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x5x5x1x96x1x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,291;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x112x112x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,263;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:92;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,8,64,16,4,1,1,2,1,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,1,1,1,8,1,32,136;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,8,64,32,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,4,1,1,8,1,32,106;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x112x112x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x113x113x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x115x115x1x5x5x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x115x115x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,9,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x115x115x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,5,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,8,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:193;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x115x115x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x125x125x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x128x128x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x128x128x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x128x128x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x128x128x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x128x128x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x128x128x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x128x128x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x96x128x128x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x128x128x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x128x128x1x5x5x1x96x1x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x128x256x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x128x256x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x129x129x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x12x12x1x3x3x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,256,16,32,32,2,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,16,1,16,1,16,35[10];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x131x131x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x131x131x1x5x5x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x139x139x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x139x139x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x139x139x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x139x139x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x139x139x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x139x139x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x139x139x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x139x139x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x13x13x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x140x140x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x140x140x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x140x140x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x140x140x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x140x140x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x141x141x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x141x141x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x141x141x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, OddC, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x141x141x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x141x141x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x143x143x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x143x143x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x145x145x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x145x145x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:69;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x96x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[4];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,10,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[10];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,174[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[4];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[8];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x14x14x1x1x1x1x480x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:199;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:189;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[9];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x480x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[10];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:65;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:85;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,32,16,64,16,4,1,1,2,1,0,0,1,0,0,1,8,2,1,1,2,1,128,1,2,1,1,1,8,1,32,134[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,16,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,93[1];ConvBinWinogradRxSf2x3:58;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:80;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:93;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:70;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:66;ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[8];ConvBinWinogradRxSf2x3:108;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,23;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:145;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:55;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:140;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:75;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x96x14x14x1x1x1x1x608x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[5];ConvBinWinogradRxSf2x3:71;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:104;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,230;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x14x14x1x2x2x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:120;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x176x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x3x3x1x208x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x3x3x1x208x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x208x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x14x14x1x3x3x1x208x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x14x14x1x3x3x1x208x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x208x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x14x14x1x3x3x1x208x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:106;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x14x14x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x14x14x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x14x14x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x3x3x1x208x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x208x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x14x14x1x3x3x1x208x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x14x14x1x3x3x1x208x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x14x14x1x3x3x1x208x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x3x3x1x208x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x14x14x1x3x3x1x208x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x208x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x14x14x1x3x3x1x208x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:179;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x14x14x1x3x3x1x208x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:175;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x14x14x1x3x3x1x208x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x14x14x1x3x3x1x208x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x208x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:101;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x384x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x3x3x1x480x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:199;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+8
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:71;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x14x14x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x96x14x14x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x14x14x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x14x14x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x14x14x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x14x14x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x14x14x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x14x14x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x96x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x96x1536x1536x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x96x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x96x1536x1536x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,256,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,4,1,1,4,1,64,45;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x96x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x96x1536x1536x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x96x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x96x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x96x1536x1536x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x15x15x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x164x164x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x164x164x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x165x165x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x165x165x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x96x165x165x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x165x165x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x165x165x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x166x166x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x96x166x166x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x166x166x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x166x166x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x169x169x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x16x16x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x16x16x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:135;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x96x16x16x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x16x16x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x16x16x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x16x16x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x16x16x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x16x16x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x171x171x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x17x17x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x17x17x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,211;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x17x17x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x17x17x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x17x17x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x17x17x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x17x17x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+2
2x96x17x17x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x96x17x17x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x17x17x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x17x17x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x17x17x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x17x17x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x17x17x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:198;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x17x17x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x17x17x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x17x17x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x18x18x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x18x18x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,42;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,2,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[2];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x18x18x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x18x18x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x18x18x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x18x18x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x192x192x1x3x3x1x192x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x1x1x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x1x1x1x1x1x1x2301x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x96x1x1x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x96x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73
2x96x2048x2048x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x96x2048x2048x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x96x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x96x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
2x96x2048x2048x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1>
2x96x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x96x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x96x2048x2048x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+128
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvBinWinogradRxSf2x3:213;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+128
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x207x207x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+-1
2x96x20x20x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:169;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x212x212x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,178;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x212x212x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[3];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x212x212x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:211;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x212x212x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+128
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvBinWinogradRxSf2x3:197;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+128
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x217x217x1x11x11x1x3x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+-1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvBinWinogradRxSf2x3:251;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x96x218x218x1x7x7x1x3x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x218x218x1x7x7x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:155;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x218x218x1x7x7x1x3x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 112, 32, Default, 8, 4, 7, 4, 4, 7, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,9,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x218x218x1x7x7x1x3x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x224x224x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x128x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x96x224x224x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x16x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:236;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[7];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:197;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x224x224x1x7x7x1x3x1x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,309;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,191[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x256x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,8,64,16,4,1,1,2,2,1,0,0,1,0,1,1,8,1,1,8,1,32,1,1,2,1,1,8,1,32,121;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,5,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[5];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x224x224x1x7x7x1x3x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x224x224x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvBinWinogradRxSf2x3:216;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x32x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[4];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x224x224x1x7x7x1x3x4x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x224x224x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,205;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,6,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[6];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x224x224x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x64x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x224x224x1x7x7x1x3x8x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x227x227x1x11x11x1x3x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,275;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x227x227x1x11x11x1x3x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x227x227x1x11x11x1x3x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,154;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x227x227x1x11x11x1x3x50x5x5x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,10,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[10];ConvBinWinogradRxSf2x3:196;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 48, 32, Default, 8, 4, 3, 4, 4, 3, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
2x96x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x24x16x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x24x16x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,318;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,0,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x96x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x96x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x24x16x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x10x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x10x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x10x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x11x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x11x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x11x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x12x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x12x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x12x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x13x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x13x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x13x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x14x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x14x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x14x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x15x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x15x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x15x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x16x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x16x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, OddC, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x24x16x1x1x3x1x96x16x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x17x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x17x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x17x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x18x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x18x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x18x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x19x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x19x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x19x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x1x3x1x96x1x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x96x24x16x1x1x3x1x96x1x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x1x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x20x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x20x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x20x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x21x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x21x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x21x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x22x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x22x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x22x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x23x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x23x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x23x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x24x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x24x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x24x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x25x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x25x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x25x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x26x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x26x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x26x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x27x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x27x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x27x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x28x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x28x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x28x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x24x16x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x96x24x16x1x1x3x1x96x29x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x29x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x29x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x96x24x16x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x2x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x2x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x24x16x1x1x3x1x96x2x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x24x16x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x30x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x30x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x30x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x31x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x31x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x31x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x24x16x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x24x16x1x1x3x1x96x32x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x32x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x32x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x33x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x33x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x33x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
2x96x24x16x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x34x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x34x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x34x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x35x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x35x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x35x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x36x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x36x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x36x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x37x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x37x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x1x3x1x96x37x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,7,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x3x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x3x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x3x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x24x16x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x96x24x16x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x24x16x1x1x3x1x96x4x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x4x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x4x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x5x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x1x3x1x96x5x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x5x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x6x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x6x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x6x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x7x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x7x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x7x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x8x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x8x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x8x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x1x3x1x96x9x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x1x3x1x96x9x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x1x3x1x96x9x0x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x10x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x10x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x10x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x11x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x11x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x11x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x12x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x12x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x12x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x13x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x13x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x13x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x14x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x14x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x14x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x15x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x15x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x15x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x16x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x16x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x16x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x17x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x17x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x17x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x18x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x18x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x18x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x19x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x19x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x19x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+8
2x96x24x16x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x3x1x1x96x1x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x1x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x1x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x24x16x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x20x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x20x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x20x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x21x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x21x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x21x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x22x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x22x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x22x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x23x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x23x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x23x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x24x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x24x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x24x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x25x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x25x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x25x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x26x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x26x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x26x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x27x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x27x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x27x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x28x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x28x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x28x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x29x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x29x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x29x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x24x16x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x24x16x1x3x1x1x96x2x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x2x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x2x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x30x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x30x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x30x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x96x24x16x1x3x1x1x96x31x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x31x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x31x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x32x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x32x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x32x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+16
2x96x24x16x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x33x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x33x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x33x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x34x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x34x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x34x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x35x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x35x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x35x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x36x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x36x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x36x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x37x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x37x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x24x16x1x3x1x1x96x37x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x16x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x96x24x16x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x3x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x3x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x3x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x4x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x24x16x1x3x1x1x96x4x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x4x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x5x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x5x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x5x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x6x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x6x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x6x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x24x16x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x7x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x24x16x1x3x1x1x96x7x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x7x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x24x16x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x8x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,321;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x8x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x8x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x24x16x1x3x1x1x96x9x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x24x16x1x3x1x1x96x9x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x24x16x1x3x1x1x96x9x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x24x24x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:123;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x253x253x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x253x253x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x256x256x1x1x1x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:177;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x195x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x256x256x1x1x1x1x240x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x240x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x27x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,8,1,1,4,1,1,16,1,8,164;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x256x256x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x256x256x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x54x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x256x256x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x256x256x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x256x256x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x256x256x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x256x256x1x5x5x1x96x4x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x256x256x1x7x7x1x192x1x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x256x256x1x7x7x1x96x1x3x3x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x257x257x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x259x259x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x259x259x1x5x5x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x26x26x1x3x3x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:72;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x27x27x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x27x27x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x27x27x1x5x5x1x256x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x27x27x1x5x5x1x256x50x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, OddC, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x27x27x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, OddC, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x27x27x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x27x27x1x5x5x1x256x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,140;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[5];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x96x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,10,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[10];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,82[1];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[6];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,8,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[8];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,182;ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:96;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,176[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[5];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[8];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,1,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x28x28x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,71;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x56x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x1x1x1x56x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x56x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:105;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x224x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[8];ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x28x28x1x3x3x1x32x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,124;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+128
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x28x28x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x96x28x28x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[1];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,4,16,16,1,1,1,2,2,1,0,4,1,0,1,1,1,1,1,4,1,64,1,1,1,1,1,4,1,64,69[4];ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x96x28x28x1x3x3x1x32x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x96x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[3];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x28x28x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,115[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:206;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x28x28x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x28x28x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:75;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:107;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:67;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:152;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,1,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,41[1];ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:99;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:95;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x28x28x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,32,32,64,16,4,1,1,2,1,1,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,5,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x96x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+32
2x96x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+1
2x96x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,4,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[4];ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:52;ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:132;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:87;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+32
2x96x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+16
2x96x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+8
2x96x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:88;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,1,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,182[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,5,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[5];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:214;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x28x28x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,4,64,32,1,1,1,1,1,1,0,4,1,0,1,1,4,1,1,4,1,32,1,1,1,1,1,4,1,32,49[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+16
2x96x28x28x1x5x5x1x32x6x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,292[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x28x28x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x28x28x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 128, 32, Default, 8, 1, 8, 4, 8, 4, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x28x28x1x5x5x1x96x64x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x28x28x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 256, 32, Default, 8, 1, 16, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+64
2x96x28x28x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x28x28x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x293x293x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x293x293x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7]
2x96x293x293x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x293x293x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x96x293x293x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x293x293x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x293x293x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x293x293x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x293x293x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x293x293x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x293x293x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x293x293x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x96x293x293x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x293x293x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x293x293x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x293x293x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10]
2x96x293x293x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x293x293x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x293x293x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x293x293x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x294x294x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6]
2x96x294x294x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x294x294x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x294x294x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x294x294x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x294x294x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x294x294x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x294x294x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x294x294x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x96x294x294x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x294x294x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,4,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x294x294x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x294x294x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x29x29x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x29x29x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,64,128,16,32,32,2,1,1,1,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,51[1];ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x29x29x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x30x30x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x30x30x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:152;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:146;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x31x31x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x96x31x31x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x31x31x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x31x31x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x31x31x1x5x5x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x32x32x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:85;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x32x32x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,1,1,4,1,64,86;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x32x32x1x1x1x1x576x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:76;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x32x32x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x32x32x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:100;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x32x32x1x3x3x1x32x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:23;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x32x32x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x32x32x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x32x32x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:147;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:145;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x33x33x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, OddC, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x33x33x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x33x33x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+8
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x33x33x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x33x33x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x33x33x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, OddC, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x33x33x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x33x33x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:110;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x96x34x34x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x34x34x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x34x34x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,21;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x34x34x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x34x34x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x34x34x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x34x34x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,55;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x96x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x35x35x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:51;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x35x35x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:77;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:122;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:54;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:65;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[3];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x35x35x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:100;ConvBinWinogradRxSf3x2:50;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:159;ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:144;ConvBinWinogradRxSf3x2:53;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:76;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x35x35x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,312[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x35x35x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x35x35x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x35x35x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x35x35x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,8,16,16,4,1,1,2,2,1,0,3,1,0,1,1,2,1,1,8,1,32,1,1,2,1,1,8,1,32,209[3];ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:102;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x35x35x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x35x35x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:84;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:59;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:88;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:35;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+1
2x96x35x35x1x3x3x1x64x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x64x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x35x35x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x35x35x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x35x35x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
2x96x35x35x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:72;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:105;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x35x35x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,8,64,16,4,1,1,1,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,179[3];ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:53;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+4
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[2];ConvBinWinogradRxSf2x3:63;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:232;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,155[3];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x35x35x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:125;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,187;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,121[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:115;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,32,16,64,16,4,1,1,1,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,219[1];ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x35x35x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,8,32,32,2,1,1,2,2,0,0,0,0,0,1,4,1,1,1,2,1,128,1,4,1,1,1,2,1,128,15;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,73;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,1,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,13[1];ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:222;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,215[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,145;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x35x35x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,26[1];ConvBinWinogradRxSf3x2:103;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x35x35x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x84x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x86x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,100;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x35x35x1x3x3x1x96x86x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x35x35x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,169;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:121;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:114;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x35x35x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x35x35x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,31[2];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x37x37x1x4x4x1x96x1x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x40x40x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9]
2x96x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10]
2x96x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x448x448x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7]
2x96x448x448x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x448x448x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9]
2x96x448x448x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x96x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x448x448x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x1024x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8]
2x96x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10]
2x96x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x451x451x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[7]
2x96x451x451x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+2
2x96x451x451x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x451x451x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10]
2x96x451x451x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x512x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9]
2x96x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,84[1];ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8]
2x96x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x451x451x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x48x32x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x48x32x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x96x48x32x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x48x32x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x48x32x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x48x32x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x48x32x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 64, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+4
2x96x48x32x1x1x1x1x288x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x288x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x288x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x288x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x48x32x1x1x1x1x288x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x48x32x1x1x1x1x288x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x48x32x1x1x1x1x288x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x288x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x288x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x96x48x32x1x1x1x1x288x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x48x32x1x1x1x1x288x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x48x32x1x1x1x1x288x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x288x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x288x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x288x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x288x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x104x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x112x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x136x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x144x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x152x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x160x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x168x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x176x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x184x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x192x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x200x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x224x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x232x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x240x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x248x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x264x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x272x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x288x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x296x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
2x96x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x72x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x80x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x88x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x384x96x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x48x32x1x1x1x1x40x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x1x1x40x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x1x1x40x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x1x1x40x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x40x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x1x1x40x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x1x1x40x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x40x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x40x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x40x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x40x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x1x1x48x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x48x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x48x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x96x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x48x32x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x10x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x11x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x12x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x13x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x14x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x15x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x16x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x17x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x18x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x19x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x1x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x20x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x21x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x22x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x23x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x3x1x96x24x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x25x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x26x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x27x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x28x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x29x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x48x32x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x2x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x30x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x31x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x96x48x32x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x32x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x96x48x32x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x33x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x1x3x1x96x34x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x1x3x1x96x35x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x96x48x32x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x1x3x1x96x36x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+64
2x96x48x32x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x1x3x1x96x37x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x1x3x1x96x3x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x4x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x5x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x6x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x7x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x8x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x1x3x1x96x9x0x2x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x2x2x1x192x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x13x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x15x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x17x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x19x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x48x32x1x2x2x1x192x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x21x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x24x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x25x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x26x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x27x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x28x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x29x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x2x2x1x192x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x31x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x35x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x36x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x37x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x3x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x2x2x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x48x32x1x2x2x1x192x5x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x2x2x1x192x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x2x2x1x192x9x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x10x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x11x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x12x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x13x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x14x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x15x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x16x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x17x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x18x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x19x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x48x32x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x1x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x20x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,8,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x96x48x32x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x21x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x22x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,3,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x23x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x24x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,10,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x25x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x26x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x27x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x28x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,3,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x29x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x30x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x31x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x32x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x48x32x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x1x1x96x33x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x34x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x35x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x36x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x1x1x96x37x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x1x1x96x3x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x4x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x5x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x48x32x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x6x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x7x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x8x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x1x1x96x9x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x3x1x96x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x96x48x32x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+32
2x96x48x32x1x3x3x1x96x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x96x48x32x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x48x32x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x96x48x32x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x48x32x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x48x32x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x32x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x48x32x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x48x32x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x48x32x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x48x32x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+8
2x96x48x32x1x3x3x1x96x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x48x32x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x48x32x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x32x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x48x32x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x48x32x1x3x3x1x96x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x48x32x1x3x3x1x96x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x48x48x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,256,32,16,64,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,8,1,1,8,1,32,166;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x48x48x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,158;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x48x48x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x48x48x1x7x7x1x96x4x3x3x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x49x49x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x4x16384x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x4x196x1x1x1x1x193x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:122;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x4x49x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x4x4x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x4x4x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x4x4x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x50x50x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x512x512x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x512x512x1x1x1x1x195x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, OddC, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x512x512x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x512x512x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x512x512x1x1x1x1x272x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x1x1x1x42x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x512x512x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x1x1x1x54x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,16,32,32,4,1,1,2,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,4,1,1,16,1,16,131;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x512x512x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x512x512x1x1x1x1x96x1x0x0x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x512x512x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x512x512x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x512x512x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:256;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x512x512x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x512x512x1x5x5x1x96x4x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x512x512x1x7x7x1x96x1x3x3x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x53x53x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x53x53x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x53x53x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x53x53x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x53x53x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:167;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[6];ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x54x54x1x1x1x1x16x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,158;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,79;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,32,32,64,16,4,1,1,2,1,0,0,0,0,0,1,8,4,1,1,4,1,64,1,2,1,2,1,16,1,16,256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:218;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,16,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,83;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:126;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,16,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,62;ConvBinWinogradRxSf3x2:81;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,233[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,16,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,141[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x50x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x55x55x1x11x11x1x3x64x0x0x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[2];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 1, 1>+1
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[7];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[4];ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:237;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,59;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,12;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[5];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[2];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,2,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[2];ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:187;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:188;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,92[9];ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,15;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,2,1,1,4,1,64,50;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[3];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[3];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:208;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,206;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,106;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:78;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:138;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,256,64,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,1;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x195x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x56x56x1x1x1x1x196x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,133;ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,4,4,1,1,8,1,32,1,4,1,1,1,8,1,32,225;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:49;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:74;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,40;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:91;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x272x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,64,32,16,16,4,1,1,2,2,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,2,1,1,8,1,32,54;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x272x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x272x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:213;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x27x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x96x56x56x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x56x56x1x1x1x1x304x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:241;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x304x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[6];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x56x56x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,31;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,21[2];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,0,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,218;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:46;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:181;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,314;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,170;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,2,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,212;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Stride1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x56x56x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:78;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x56x56x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,53[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:55;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x56x56x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x56x56x1x2x2x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x2x2x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x56x56x1x2x2x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,139;ConvBinWinogradRxSf3x2:164;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x56x56x1x2x2x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x2x2x1x192x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x56x56x1x2x2x1x192x98x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+64
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x56x56x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x56x56x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x96x56x56x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x56x56x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x3x3x1x96x1x1x1x0x4x4x0x1x1x0x0x96xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 32>
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x56x56x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x56x56x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x56x56x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,119;ConvBinWinogradRxSf3x2:150;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x56x56x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:43;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 8>+128
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+32
2x96x56x56x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x56x56x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x56x56x1x3x3x1x96x98x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x3x3x1x96x98x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x16x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x32x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x56x56x1x7x7x1x3x128x3x3x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,256,64,16,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,4,1,64,1,4,1,1,1,4,1,64,99[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,9,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,149[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x50x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,289;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,6,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,1,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,175;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,2,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,140[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+1
2x96x57x57x1x11x11x1x3x64x4x4x0x4x4x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x57x57x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x57x57x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:50;ConvBinWinogradRxSf3x2:48;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x64x128x1x1x1x1x480x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:51;ConvBinWinogradRxSf3x2:45;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x64x128x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x64x128x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:212;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x96x64x128x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, OddC, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x96x64x64x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x64x64x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x64x64x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x64x64x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,145;ConvBinWinogradRxSf3x2:196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x64x64x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x64x64x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x661x661x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,2,1,1,4,1,32,1,2,1,1,1,8,1,16,82;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x96x661x661x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10]
2x96x662x662x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,16,32,16,16,4,1,1,2,1,1,0,0,0,0,1,4,4,1,1,8,1,16,1,4,1,1,1,8,1,16,78;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>+1
2x96x662x662x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_Large_Tensor<256, 128, 128, 32, Default, 8, 2, 2, 1, 2, 1, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5>+128
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:61;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:45;ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:64;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x69x69x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x69x69x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:108;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x69x69x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:174;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x69x69x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:221;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:68;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:146;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x96x69x69x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x69x69x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x96x69x69x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x69x69x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x69x69x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x69x69x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x69x69x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x69x69x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:223;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x69x69x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x69x69x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x69x69x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[10]
2x96x69x69x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x69x69x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x69x69x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:224;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x96x69x69x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:234;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x69x69x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x70x70x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,1,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,14;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[8]
2x96x70x70x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x70x70x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x70x70x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x70x70x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x70x70x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:219;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,9,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x70x70x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
2x96x70x70x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x70x70x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,1,0,0,0,0,1,4,4,1,1,4,1,64,1,2,1,1,1,8,1,32,6;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,128,16,32,32,2,1,2,1,2,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,8,1,16,1,16,11[7]
2x96x70x70x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x70x70x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x70x70x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,74;ConvBinWinogradRxSf3x2:216;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x70x70x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,4,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,88[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:66;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x71x71x1x3x3x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x96x71x71x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x71x71x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x71x71x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x71x71x1x3x3x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x71x71x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:7;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x96x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x71x71x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x71x71x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x71x71x1x3x3x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:242;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[8];ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x71x71x1x3x3x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,9,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[9];ConvBinWinogradRxSf2x3:44;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,6,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:82;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,4,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,4,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:161;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,3,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,9,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:180;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,4,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:220;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x72x72x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,10,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[10];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x73x73x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x73x73x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x73x73x1x3x3x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:209;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:47;ConvBinWinogradRxSf3x2:123;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:217;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x73x73x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x73x73x1x3x3x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,201[1];ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:52;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x73x73x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+128
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:248;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,6,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,32,16,16,16,4,1,1,2,1,1,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,76[1];ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+4
2x96x73x73x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[6];ConvBinWinogradRxSf2x3:48;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvBinWinogradRxSf2x3:25;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x73x73x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[10];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:207;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x73x73x1x3x3x1x64x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[4];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,64[1];ConvBinWinogradRxSf3x2:159;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>+2
2x96x73x73x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,6,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,3,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[3];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,32,32,32,2,1,1,1,2,1,0,0,0,1,1,16,1,1,1,2,4,32,1,4,2,1,1,8,1,32,22;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,8,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:42;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:210;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,9,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[9];ConvBinWinogradRxSf2x3:62;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:168;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x73x73x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[7];ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x74x74x1x2x2x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, OddC, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:255;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,10,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[10];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:252;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,5,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+16
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,229;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,32,64,32,16,16,4,1,1,1,2,1,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,86;ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,8,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[8];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 64, 4, Default, 4, 2, 1, 4, 2, 4, 1, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:165;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,32,32,16,16,4,1,1,1,1,0,0,5,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,59[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:254;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,2,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,157;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,143[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,64,16,16,16,4,1,1,1,2,0,0,7,0,0,1,1,1,2,1,16,1,16,1,1,1,4,1,16,1,16,55[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:251;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,77[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:250;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,2,1,0,0,7,0,0,1,1,1,8,1,16,1,16,1,1,1,4,1,16,1,16,23[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,64,64,16,16,16,4,1,1,2,2,1,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,62;ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,5,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,245;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,256,64,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,109;ConvBinWinogradRxSf3x2:227;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,87[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,1,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:211;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x74x74x1x3x3x1x64x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,1,32,128,16,32,32,2,1,1,1,1,0,0,6,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,47[6];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
2x96x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x96x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,111
2x96x768x768x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183
2x96x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x96x768x768x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,205
2x96x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,4,1,1,4,1,64,105
2x96x768x768x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,128,16,32,32,2,1,1,2,2,0,0,0,0,0,1,4,2,1,1,4,1,64,1,4,2,1,1,4,1,64,11
2x96x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219
2x96x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,125
2x96x768x768x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,25
2x96x7x7x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<128, 16, 64, 64, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:47;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 1, 1, 1>+1
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[1];ConvBinWinogradRxSf2x3:43;ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:63;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x288x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,10,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[10];ConvBinWinogradRxSf2x3:49;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,10,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[10];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:83;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x288x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:171;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:27;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:154;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:61;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:117;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:90;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:77;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,224;ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:166;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:79;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,87;ConvBinWinogradRxSf3x2:173;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:205;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x96x7x7x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:59;ConvBinWinogradRxSf3x2:67;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x96x7x7x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,120;ConvBinWinogradRxSf3x2:170;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:60;ConvBinWinogradRxSf3x2:116;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:172;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>+1
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,0,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,30;ConvBinWinogradRxSf3x2:191;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
2x96x7x7x1x1x1x1x576x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,3,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[3];ConvBinWinogradRxSf2x3:57;ConvBinWinogradRxSf3x2:54;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,1,4,1,8,1,32,322;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,216;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,9,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[9];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+2
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,159;ConvBinWinogradRxSf3x2:42;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,8,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,118[8];ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,32,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,2,1,1,8,1,32,66;ConvBinWinogradRxSf3x2:62;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[4];ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,16,64,32,16,16,4,1,1,1,2,0,0,0,0,0,1,4,1,1,1,8,1,16,1,4,4,1,1,8,1,16,70;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+32
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,252;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+8
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,32,16,64,16,4,1,1,1,1,0,0,1,0,0,1,4,2,1,1,4,1,32,1,4,1,1,1,4,1,32,221[1];ConvBinWinogradRxSf3x2:70;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,128,32,16,64,4,1,1,1,1,0,0,0,0,0,1,4,1,1,1,8,1,32,1,4,4,1,1,8,1,32,172;ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[5];ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,0,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,75;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 1, 1>+1
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,64,32,32,16,16,4,1,1,2,1,0,0,0,0,0,1,4,2,1,1,8,1,32,1,4,1,1,1,8,1,32,58;ConvBinWinogradRxSf3x2:60;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x7x7x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,1,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[1];ConvBinWinogradRxSf2x3:41;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 32, 32, Default, 8, 1, 1, 2, 2, 2, 2, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 2>+64
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x7x7x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 4>+32
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x7x7x1x3x3x1x96x64x1x1x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+8
2x96x7x7x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x96xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 16, 32, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x96x80x120x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x80x120x1x3x3x1x32x47x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,256,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,2,8,1,1,8,1,32,1,2,1,1,1,8,1,32,5;ConvBinWinogradRxSf3x2:228;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x80x120x1x3x3x1x32x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,1,128,32,16,32,32,2,1,1,2,1,0,0,0,0,0,1,4,4,1,1,4,1,32,1,4,1,1,1,4,1,32,39;ConvBinWinogradRxSf3x2:239;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, OddC, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x83x83x1x1x1x1x42x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
2x96x83x83x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x83x83x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x83x83x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:56;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x83x83x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 4, 2, 2, 1, 4, 1, 4, 1, 1, 1>+64
2x96x85x85x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:58;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>+1
2x96x85x85x1x5x5x1x96x64x2x2x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x86x86x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xB=ConvBinWinogradRxSf2x3:64;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>+1
2x96x86x86x1x7x7x1x96x64x3x3x0x2x2x0x1x1x0x0x96xNCHWxFP32xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
2x96x8x8x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,177;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x96x64x1x1x1x1x192x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+128
2x96x96x64x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Filter1x1Stride1Pad0, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+128
2x96x96x64x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x96x64x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x96x64x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x96x64x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x96x64x1x1x1x1x192x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x96x64x1x1x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x96x64x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,210[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x96x64x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,211[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,4,1,4,1,64,294;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,256,32,32,32,8,1,2,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,4,1,4,1,64,266;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>+1
2x96x96x64x1x1x1x1x192x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x96x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,64,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,4,1,2,1,8,1,32,246;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
2x96x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x40x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+32
2x96x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,306;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x40x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
2x96x96x64x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x96x96x64x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
2x96x96x64x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x13x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 128x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x18x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,220[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
2x96x96x64x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,286;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+16
2x96x96x64x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
2x96x96x64x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x26x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x30x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x96x96x64x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,184[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
2x96x96x64x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x37x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,186[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
2x96x96x64x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x5x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x1x1x96x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x96x96x64x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x10x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x11x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x12x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+128
2x96x96x64x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x13x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x14x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x15x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x16x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x17x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x96x96x64x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x18x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x19x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x20x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x22x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x23x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x25x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x27x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x28x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x29x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x1x3x1x96x2x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x30x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x1x3x1x96x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x33x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x35x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x1x3x1x96x3x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x1x3x1x96x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x1x3x1x96x6x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x96x64x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x1x3x1x96x7x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x1x3x1x96x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x96x64x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x1x3x1x96x9x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x10x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x96x64x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x11x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x12x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x13x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x14x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x15x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_DirectLoad<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x17x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+128m, 128, 64, 32, Default, 8, 2, 2, 4, 4, 2, 4, 1, 1, 2>+-1
2x96x96x64x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x18x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x3x1x1x96x19x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,64,1,2,1,2,1,16,1,16,285;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x1x1x96x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x20x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x3x1x1x96x21x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x22x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x23x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x24x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x25x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x27x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x28x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x29x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,16,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,2,1,4,1,64,1,4,1,2,1,4,1,64,180[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,277;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,1,1,4,1,64,215;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x1x1x96x2x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x30x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x31x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x32x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x33x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x34x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x35x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x36x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x37x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+128
2x96x96x64x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x1x1x96x3x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,4,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x1x1x96x4x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,32,32,16,16,16,1,1,2,1,0,1,7,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,241[7];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x96x64x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, OddC, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x1x1x96x5x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x6x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x7x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,32,32,32,8,1,1,1,1,0,1,4,0,0,1,8,1,1,1,4,1,64,1,8,1,1,1,4,1,64,232[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x1x1x96x8x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,207[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+64
2x96x96x64x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x1x1x96x9x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,2,1,8,1,32,208[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x10x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x96x64x1x3x3x1x96x10x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x96x64x1x3x3x1x96x11x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x96x64x1x3x3x1x96x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x96x64x1x3x3x1x96x13x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x14x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+64
2x96x96x64x1x3x3x1x96x14x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x15x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x15x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x17x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x17x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x18x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,1,0,0,0,0,1,8,2,1,1,4,1,32,1,4,1,2,1,8,1,16,313;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x96x96x64x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,242;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 32, 64, Default, 8, 1, 1, 8, 8, 8, 8, 1, 1, 4>+16
2x96x96x64x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x20x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x20x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x21x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x21x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x22x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x23x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x24x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x25x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x26x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x26x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+1
2x96x96x64x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x27x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x27x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x28x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x28x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x29x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x29x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,1,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,325;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x96x64x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x3x1x96x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x96x96x64x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,1,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,239;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x30x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x30x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x31x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x31x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,0,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,169[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x33x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,179[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x33x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x34x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x35x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x36x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,256,32,32,32,8,1,2,2,2,0,1,1,0,0,1,4,1,4,1,8,1,32,1,4,1,8,1,8,1,32,171[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x36x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, OddC, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x96x64x1x3x3x1x96x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x37x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,183;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, OddC, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,1,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,236[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+32
2x96x96x64x1x3x3x1x96x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x96x64x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,5,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[5];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x3x1x96x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x5x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,4,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[4];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<128, 16, 64, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 4>+-1
2x96x96x64x1x3x3x1x96x5x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,255;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, OddC, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x96x64x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,209;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 64, 64, Default, 8, 2, 2, 8, 8, 8, 8, 1, 1, 2>+-1
2x96x96x64x1x3x3x1x96x6x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x7x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,3,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,213[3];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 256, 32, 64, Default, 8, 2, 1, 8, 8, 8, 8, 1, 1, 8>+-1
2x96x96x64x1x3x3x1x96x7x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,1,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,297;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x96x96x64x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,235[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x96x64x1x3x3x1x96x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x64x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,1,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,269;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x96x96x64x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,219;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x96x96x64x1x3x3x1x96x9x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,1,128,128,32,32,32,8,1,1,2,2,0,1,2,0,0,1,4,1,4,1,8,1,32,1,4,1,4,1,8,1,32,181[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3_DirectLoad<256, 64, 128, 64, Default, 8, 1, 2, 8, 8, 8, 8, 1, 1, 8>+32
2x96x96x64x1x3x3x1x96x9x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,1,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x96x96x96x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x96x96x96x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,256,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,4,1,1,4,1,64,140;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x972x1x1x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x972x32x32x1x1x1x1x174x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x972x64x64x1x1x1x1x174x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,16,32,32,4,1,1,2,2,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,8,1,1,16,1,16,117;ConvBinWinogradRxSf3x2:185;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
2x972x7x7x1x3x3x1x972x1x1x1x0x1x1x0x1x1x0x0x972xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x976x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x976x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:186;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x976x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:194;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x976x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,196;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x976x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,64,16,64,32,4,1,1,1,2,0,0,0,0,0,1,4,4,1,1,4,1,64,1,4,1,1,1,4,1,64,92;ConvBinWinogradRxSf3x2:233;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x976x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,1,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[1];ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x97x64x64x1x1x1x1x278x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x984x128x128x1x1x1x1x1968x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:249;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x984x1x1x1x1x1x1x246x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:9;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x984x256x256x1x3x3x1x984x1x1x1x0x1x1x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:245;ConvBinWinogradRxSf3x2:256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x984x28x28x1x1x1x1x1968x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,128,8,32,32,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,8,1,32,1,1,4,1,1,8,1,32,118;ConvBinWinogradRxSf3x2:203;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x984x56x56x1x3x3x1x984x1x1x1x0x2x2x0x1x1x0x0x3xNCHWxFP16xF=ConvBinWinogradRxSf2x3:79;ConvBinWinogradRxSf3x2:46;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x98x28x28x1x5x5x1x98x1x2x2x0x1x1x0x1x1x0x0x98xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, OddC, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x990x1x1x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x990x1x1x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x990x32x32x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,128,32,16,64,16,4,1,1,1,1,0,0,0,1,0,1,1,8,1,1,16,1,16,1,1,2,1,1,16,1,16,138;ConvBinWinogradRxSf3x2:44;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x990x32x32x1x5x5x1x990x1x2x2x0x1x1x0x1x1x0x0x990xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x990x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,0,0,0,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,157;ConvBinWinogradRxSf3x2:10;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 2, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x992x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:253;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 2, 1, 1>+1
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:136;ConvBinWinogradRxSf3x2:163;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x992x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+4
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:93;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:57;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:68;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:109;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,8,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[8];ConvBinWinogradRxSf2x3:135;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x992x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,270;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,218[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,1,2,1,4,1,64,146;ConvBinWinogradRxSf3x2:201;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,72[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:127;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:200;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x992x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:113;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:134;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:102;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:111;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:136;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x992x14x14x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, OddC, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,240;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,184;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,256,128,32,32,32,8,2,1,2,2,0,1,1,0,0,1,4,1,8,1,8,1,32,1,4,1,4,1,8,1,32,166[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,1,2,1,4,1,64,101;ConvBinWinogradRxSf3x2:238;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>+1
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,256,128,32,32,32,8,2,1,2,2,0,0,0,0,0,1,8,4,1,1,4,1,64,1,8,2,1,1,4,1,64,74;ConvBinWinogradRxSf3x2:231;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,256,128,16,32,32,8,2,1,2,2,0,0,2,0,0,1,4,1,4,1,4,1,64,1,4,1,2,1,4,1,64,73[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,0,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,63;ConvBinWinogradRxSf3x2:230;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:229;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,128,16,32,32,2,1,1,1,2,0,0,3,0,0,1,1,1,4,1,16,1,16,1,1,1,8,1,16,1,16,25[3];ConvBinWinogradRxSf2x3:134;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+32
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:247;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:204;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:124;ConvBinWinogradRxSf3x2:155;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,33[1];ConvBinWinogradRxSf3x2:226;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 2, 1, 1>+1
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:235;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:126;ConvBinWinogradRxSf3x2:128;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x992x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,210;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,128,32,32,32,8,1,1,2,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,8,2,1,1,4,1,64,112;ConvBinWinogradRxSf3x2:244;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:236;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+2
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,238[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+8
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,203[1];ConvBinWinogradRxSf3x2:162;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>+2
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:153;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,3,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[3];ConvBinWinogradRxSf2x3:151;ConvBinWinogradRxSf3x2:137;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:182;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 2, 1, 1>+4
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:151;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:138;ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,310[3];ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,32,32,64,16,4,1,1,1,1,0,0,0,0,0,1,8,2,1,1,4,1,32,1,8,1,1,1,4,1,32,243;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,32,32,16,16,16,1,1,2,1,0,1,1,0,0,1,4,1,2,1,8,1,32,1,4,1,1,1,8,1,32,243[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,4,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[4];ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:141;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,32,8,32,32,2,1,1,1,1,1,0,4,1,0,1,1,4,1,1,8,1,32,1,1,1,1,1,8,1,32,47[4];ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,2,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[2];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x992x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,0,1,8,2,1,1,4,1,64,1,4,1,2,1,8,1,32,278;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:147;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 2, 1, 1>+1
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:156;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_DirectLoad<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:141;ConvBinWinogradRxSf3x2:133;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+16
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+4
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,1,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,28[1];ConvBinWinogradRxSf3x2:144;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x992x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,128,32,16,32,32,2,1,1,1,1,0,0,3,0,0,1,1,1,8,1,16,1,16,1,1,1,2,1,16,1,16,41[3];ConvBinWinogradRxSf2x3:148;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
2x992x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,234;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:56;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+8
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,2,1,1,4,1,64,146;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[1];ConvBinWinogradRxSf2x3:127;ConvBinWinogradRxSf3x2:129;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,1,128,64,8,32,32,2,1,1,2,1,1,0,3,1,0,1,1,4,1,1,8,1,32,1,1,2,1,1,8,1,32,35[3];ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+8
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:41;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
2x992x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,128,16,32,32,2,1,1,1,1,0,0,1,0,0,1,1,1,2,1,16,1,16,1,1,1,8,1,16,1,16,45[1];ConvBinWinogradRxSf2x3:137;ConvBinWinogradRxSf3x2:130;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x992x7x7x1x1x1x1x128x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,298;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>+1
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,221;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[2];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,0,0,0,1,8,1,1,1,4,1,64,1,8,1,2,1,4,1,64,188;ConvBinWinogradRxSf3x2:202;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 2, 1, 1>+1
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,128,64,32,32,32,8,1,1,1,2,0,0,0,0,1,1,16,1,1,1,2,4,32,1,8,1,1,1,4,1,64,128;ConvBinWinogradRxSf3x2:195;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,128,32,32,32,8,1,1,2,1,0,0,2,0,0,1,4,1,2,1,8,1,32,1,4,1,4,1,8,1,32,126[2];ConvBinWinogradRxSf2x3:142;ConvBinWinogradRxSf3x2:160;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,64,16,16,16,4,1,1,2,2,0,0,1,0,0,1,4,1,1,1,4,1,64,1,4,1,1,1,4,1,64,65[1];ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>+2
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,16,32,32,2,1,1,1,2,0,0,0,0,1,1,8,1,1,1,2,4,32,1,4,1,1,1,4,1,64,27;ConvBinWinogradRxSf3x2:192;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
2x992x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,64,64,16,32,32,2,1,1,1,1,0,0,7,0,0,1,1,1,4,1,16,1,16,1,1,1,4,1,16,1,16,37[7];ConvBinWinogradRxSf2x3:128;ConvBinWinogradRxSf3x2:131;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,1,2,1,4,1,32,326;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,bf16,0,0,64,64,64,32,32,8,1,1,1,1,0,1,1,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,239[1];ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp16,0,1,64,64,16,16,16,4,1,1,2,2,1,0,3,1,0,1,1,4,1,1,16,1,16,1,1,4,1,1,16,1,16,206[3];ConvBinWinogradRxSf3x2:97;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 2, 1, 1>+4
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:86;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp16,0,0,64,64,64,32,32,8,1,1,1,1,0,0,2,0,0,1,4,1,4,1,16,1,16,1,4,1,4,1,16,1,16,146[2];ConvBinWinogradRxSf2x3:132;ConvBinWinogradRxSf3x2:124;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+1
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvAsmImplicitGemmGTCDynamicBwdXdlopsNHWC:bwd,nhwc,fp32,0,0,64,32,16,16,16,4,1,1,2,1,0,0,1,0,0,1,4,1,1,1,4,1,64,1,2,1,1,1,8,1,32,77[1];ConvBinWinogradRxSf3x2:73;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 1, 1, 1>+4
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:80;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvAsmImplicitGemmGTCDynamicWrwXdlopsNHWC:wrw,nhwc,fp32,0,0,32,32,32,16,16,4,1,1,1,1,0,0,7,0,0,1,1,1,4,1,32,1,8,1,1,1,4,1,32,1,8,57[7];ConvBinWinogradRxSf2x3:130;ConvBinWinogradRxSf3x2:157;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
2x992x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,bf16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,256;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp16,0,0,32,64,32,16,64,4,1,1,1,1,0,0,0,0,0,1,8,1,1,1,4,1,32,1,8,2,1,1,4,1,32,178;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x992x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvAsmImplicitGemmGTCDynamicFwdXdlopsNHWC:fwd,nhwc,fp32,0,0,128,64,8,32,32,2,1,1,1,2,0,0,2,0,1,1,4,1,1,1,2,4,32,1,2,1,1,1,4,1,64,32[2];ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1000x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x1008x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1008x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x1024x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x1024x16x16x16x1x1x1x512x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x1024x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x1024x16x16x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x1024x16x16x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x1024x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x1024x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x1024x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x1024x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x1024x16x16x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x1024x16x16x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+8
3x1024x16x16x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x1024x16x16x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+16
3x1024x30x30x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x30x30x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x1024x30x30x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x30x30x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1024x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x1024x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+8
3x1024x32x32x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x1024x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x464x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x464x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x1024x32x32x1x1x1x1x464x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x32x32x1x1x1x1x464x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x1024x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 2>+128
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 128, 32, Default, 8, 1, 4, 8, 8, 8, 8, 1, 1, 2>+128
3x1024x32x32x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x1024x32x32x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x1056x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1056x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1056x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1056x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1056x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1056x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x1056x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1056x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x1088x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1088x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1104x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1104x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1120x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1120x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x112x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x112x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x112x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x112x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x112x32x32x1x3x3x1x224x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x112x32x32x1x3x3x1x224x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1152x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1152x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1152x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1152x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x1184x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1184x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1200x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1200x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x120x16x16x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x120x16x16x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x120x16x16x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x120x16x16x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x120x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x120x32x32x1x3x3x1x120x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x120x32x32x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x120x32x32x1x3x3x1x120x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1216x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1216x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1248x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1248x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1248x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 256, 32, Filter1x1Pad0, 32, 32, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x1248x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x1280x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1280x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1280x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x120x160x8x3x3x3x128x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x128x128x128x128x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x128x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x128x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x128x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x128x15x15x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x15x15x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x128x15x15x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x15x15x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x128x16x16x16x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x16x16x16x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+16
3x128x16x16x16x2x2x2x1536x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x128x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 8, 1, 1>
3x128x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 8, 1, 1>
3x128x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x128x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x128x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x128x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x128x16x16x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x16x16x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x16x16x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x16x16x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x30x30x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x30x30x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x30x30x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x30x30x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1088x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1088x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1088x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1088x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1120x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1120x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1120x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1120x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1184x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1184x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1184x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1184x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1216x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1216x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1216x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1216x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1312x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1312x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1312x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1312x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1376x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1376x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1376x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1376x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1408x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1408x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1408x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1408x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1472x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1472x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1472x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1472x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1504x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1504x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x1504x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1504x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x128x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x128x32x32x1x1x1x1x1568x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1568x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1568x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1568x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1600x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1600x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1600x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1600x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1664x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1664x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1664x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1664x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1696x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1696x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1696x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1696x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1760x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1760x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1760x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1760x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
3x128x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x128x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x128x32x32x1x1x1x1x1856x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1856x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1856x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x1856x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1888x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1888x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x1888x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1888x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x224x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x352x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x416x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x128x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x608x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x704x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x736x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x928x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x992x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x128x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+64
3x128x32x32x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x128x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x128x32x32x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x128x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x128x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x128x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x128x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x128x32x32x1x5x5x1x832x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x128x32x32x1x5x5x1x832x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 208, 32, Default, 8, 4, 13, 4, 4, 13, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x128x32x32x1x5x5x1x832x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x5x5x1x832x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 64, 208, 32, Default, 8, 4, 13, 4, 4, 13, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x128x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x128x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x128x32x32x32x1x1x1x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x1x1x1x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x32x1x1x1x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x128x32x32x32x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 64, 128, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>
3x128x32x32x32x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x32x32x32x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x32x32x32x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x2x2x2x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x32x2x2x2x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x128x32x32x32x2x2x2x64x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>
3x128x32x32x32x2x2x2x64x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x32x32x32x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x128x32x32x32x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x32x32x32x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x128x32x32x32x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+-1
3x128x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x128x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
3x128x32x32x32x3x3x3x256x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x32x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+16
3x128x32x32x32x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x128x32x32x32x3x3x3x64x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x32x3x3x3x64x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x32x32x32x3x3x3x64x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x32x32x32x3x3x3x64x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x40x28x48x1x1x1x2x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x128x40x28x48x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x40x28x48x2x2x2x64x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>
3x128x40x28x48x2x2x2x64x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x128x40x28x48x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x128x40x28x48x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x128x40x28x48x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+32
3x128x40x28x48x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x128x40x28x48x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x128x40x28x48x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x40x28x48x3x3x3x64x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x40x28x48x3x3x3x64x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
3x128x64x64x64x1x1x1x256x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x64x64x64x1x1x1x256x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x128x64x64x64x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x128x64x64x64x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x128x64x64x64x2x2x2x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 4, 4, 1, 1>
3x128x64x64x64x2x2x2x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+64
3x128x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x128x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
3x128x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x128x64x64x64x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x128x64x64x64x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+64
3x128x64x64x64x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x128x64x64x64x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x128x80x56x96x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x1296x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1296x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1312x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1312x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1344x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1344x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1344x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1344x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1376x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1376x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1392x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1392x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x13x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x13x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1408x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1408x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1440x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1440x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1440x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1440x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x144x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x144x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x144x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
3x144x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x144x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x144x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x144x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x144x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x144x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x144x32x32x1x3x3x1x288x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x144x32x32x1x3x3x1x288x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1472x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1472x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1488x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1488x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1504x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1504x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1536x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1536x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1536x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1536x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1536x8x8x8x16x16x16x3x1x0x0x0x16x16x16x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x1536x8x8x8x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x1536x8x8x8x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
3x1536x8x8x8x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x1536x8x8x8x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x1536x8x8x8x2x2x2x512x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x1536x8x8x8x2x2x2x512x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+1
3x1568x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1568x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1584x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1584x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1600x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1600x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x160x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x160x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x160x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x160x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x160x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x160x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x3x3x1x320x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x3x3x1x320x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+128
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x160x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x160x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1632x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1632x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1632x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1632x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1664x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1664x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1680x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1680x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1696x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1696x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x16x32x32x1x3x3x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x32x32x1x3x3x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x16x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x16x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x16x480x640x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>
3x16x480x640x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>
3x16x480x640x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>
3x16x480x640x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 8, 1, 1>
3x16x480x640x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x16x480x640x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x16x480x640x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x16x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x16x480x640x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x16x480x640x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+-1
3x16x480x640x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x16x480x640x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x16x480x640x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x16x480x640x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x16x480x640x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x16x480x640x1x3x3x1x3x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x1728x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1728x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1728x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1728x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1760x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1760x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1776x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1776x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1792x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1792x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1792x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1792x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1824x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1824x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1824x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 256, 32, Filter1x1Stride1Pad0, 32, 32, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x1824x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1856x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x1856x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x1872x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1872x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1888x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1888x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1920x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1920x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x192x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x192x30x30x1x3x3x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x30x30x1x3x3x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x192x30x30x1x3x3x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x30x30x1x3x3x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x192x32x32x1x1x1x1x1008x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1008x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x192x32x32x1x1x1x1x1008x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1008x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1104x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1104x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1104x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1104x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1200x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1200x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1200x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1200x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1248x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1296x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1296x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1296x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1296x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1344x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1392x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1392x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1392x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1392x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x192x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x1488x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1488x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x1488x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1488x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1536x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1584x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1584x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1584x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1584x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1632x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1680x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1680x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1680x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1680x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x192x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x192x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1728x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1776x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1776x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x1776x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1776x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1824x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1872x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1872x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1872x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1872x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x1920x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1920x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x1920x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x1920x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x192x32x32x1x1x1x1x1968x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1968x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x1968x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x1968x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x2016x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2016x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x2016x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2016x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x2064x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2064x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x2064x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2064x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x2160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x192x32x32x1x1x1x1x2160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x2160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x192x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x336x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x336x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x336x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x336x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x432x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x432x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x432x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x432x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x192x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x624x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x624x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x624x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x624x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x192x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x192x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x672x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x720x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x720x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x720x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x720x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x816x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x816x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x816x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x816x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x864x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x912x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x912x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x912x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x912x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x192x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x192x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x192x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x1x7x1x128x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x192x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x192x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x1x7x1x160x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x192x32x32x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x224x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x224x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x320x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x192x32x32x1x3x3x1x320x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x3x3x1x48x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x192x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x192x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x192x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x192x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x192x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x192x32x32x1x7x1x1x128x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x192x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x192x32x32x1x7x1x1x160x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x192x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x192x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1968x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1968x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x1x128x128x128x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
3x1x15x15x1x3x3x1x2x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x15x15x1x3x3x1x2x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x15x15x1x3x3x1x2x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x15x15x1x3x3x1x2x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x160x56x192x3x1x3x32x2x1x0x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x1x30x30x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x30x30x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x30x30x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x30x30x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x30x30x1x3x3x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x30x30x1x3x3x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x30x30x1x3x3x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x1x30x30x1x3x3x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x1x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x1x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
3x1x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x1x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x1x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x1x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x1x32x32x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x1x32x32x1x5x20x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x20x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x20x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x20x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x5x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x1x32x32x1x5x5x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x2016x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 256, 32, Filter1x1Pad0, 32, 32, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x2016x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x2048x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x2048x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+16
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x2048x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x2048x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x2048x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x448x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
3x2048x32x32x1x3x3x1x256x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x3x3x1x256x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x3x3x1x256x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x3x3x1x256x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x3x3x1x256x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2048x32x32x1x3x3x1x256x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2064x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2064x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x208x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x208x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x208x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x208x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x2112x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2112x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x2112x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x2112x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x2160x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x2160x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x216x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>
3x216x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Filter1x1Stride1Pad0, 8, 2, 1, 8, 4, 2, 1, 1, 1, 2>+64
3x216x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>
3x216x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1, 2, 4, 2, 4, 1, 1, 2>+-1
3x21x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x21x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x21x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x21x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x224x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x3x3x1x112x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x224x32x32x1x3x3x1x112x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x224x32x32x1x3x3x1x112x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x224x32x32x1x3x3x1x112x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x224x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x224x32x32x1x7x1x1x192x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x224x32x32x1x7x1x1x256x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x224x32x32x1x7x1x1x256x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x240x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 1, 1, 1>
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Filter1x1Stride1Pad0, 32, 32, 1, 1, 4, 2, 1, 1>
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x240x32x32x1x1x1x1x60x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x240x32x32x1x3x3x1x240x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x24x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x24x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x24x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x24x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x24x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x24x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x24x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x24x32x32x1x1x1x1x54x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x24x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x24x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x24x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x24x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x24x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x24x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x24x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x24x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x24x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x256x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x15x15x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x15x15x1x3x3x1x224x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x15x15x1x3x3x1x224x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x15x15x1x3x3x1x224x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x15x15x1x3x3x1x224x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x15x15x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x15x15x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x15x15x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x15x15x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x16x16x16x1x1x1x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x256x16x16x16x1x1x1x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x256x16x16x16x1x1x1x320x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x16x16x16x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x16x16x16x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+8
3x256x16x16x16x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x256x16x16x16x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x256x16x16x16x2x2x2x1536x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x256x16x16x16x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 4, 4, 1, 1>
3x256x16x16x16x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x256x16x16x16x2x2x2x320x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x256x16x16x16x2x2x2x320x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x16x16x16x3x3x3x128x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x256x16x16x16x3x3x3x128x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
3x256x16x16x16x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x16x16x16x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
3x256x16x16x16x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x256x16x16x16x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x256x16x16x16x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
3x256x16x16x16x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x16x16x16x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x256x16x16x16x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+8
3x256x16x16x16x3x3x3x320x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x16x16x16x3x3x3x320x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x256x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
3x256x16x16x16x3x3x3x512x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x16x16x16x3x3x3x512x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+2
3x256x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>
3x256x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x256x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>
3x256x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x256x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x16x16x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x256x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x256x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x16x16x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+32
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>
3x256x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+32
3x256x20x14x24x1x1x1x2x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x20x14x24x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x20x14x24x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
3x256x20x14x24x2x2x2x320x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x20x14x24x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x256x20x14x24x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x256x20x14x24x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x256x20x14x24x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x256x20x14x24x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+4
3x256x20x14x24x3x3x3x320x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x20x14x24x3x3x3x512x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x256x20x14x24x3x3x3x512x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x256x28x28x16x1x1x3x256x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x256x28x28x16x1x1x5x256x1x0x0x2x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+8
3x256x28x28x16x1x1x7x256x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+8
3x256x28x28x4x1x1x3x256x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
3x256x28x28x4x1x1x5x256x1x0x0x2x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
3x256x28x28x4x1x1x7x256x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
3x256x30x30x1x3x3x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x30x30x1x3x3x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x30x30x1x3x3x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x30x30x1x3x3x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x256x32x32x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x256x32x32x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x21x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x256x32x32x1x1x1x1x21x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+128
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x256x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x256x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Filter1x1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x256x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x256x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x256x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x256x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x2048x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x256x32x32x1x3x3x1x2048x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x2048x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x256x32x32x1x3x3x1x2048x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+16
3x256x32x32x1x3x3x1x2048x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+16
3x256x32x32x1x3x3x1x2048x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x2048x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+16
3x256x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+32
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+32
3x256x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 32, 64, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x256x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x340x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x256x32x32x1x3x3x1x340x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x510x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x256x32x32x1x3x3x1x510x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x256x32x32x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x256x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x256x32x32x1x5x5x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x5x5x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x256x32x32x1x7x1x1x224x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x256x32x32x32x1x1x1x512x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 4, 4, 1, 1>
3x256x32x32x32x1x1x1x512x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x256x32x32x32x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x256x32x32x32x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+16
3x256x32x32x32x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x256x32x32x32x2x2x2x512x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x256x32x32x32x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x256x32x32x32x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x256x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x256x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 16, Default, 32, 32, 2, 4, 4, 4, 4, 1, 1, 1>
3x256x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x256x32x32x32x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x256x32x32x32x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x256x40x28x48x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x256x56x56x16x1x1x3x256x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+32
3x256x56x56x16x1x1x7x256x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x256x56x56x4x1x1x7x256x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+8
3x256x64x64x64x1x1x1x128x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Stride1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x256x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x288x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x288x32x32x1x3x3x1x144x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x288x32x32x1x3x3x1x144x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x288x32x32x1x3x3x1x144x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x288x32x32x1x3x3x1x144x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x288x32x32x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x1x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x1x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x1x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 64, 32, Default, 8, 2, 1, 4, 4, 2, 4, 1, 1, 2>+-1
3x288x48x32x1x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x1x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+32
3x288x48x32x1x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x1x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x1x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
3x288x48x32x1x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x1x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x1x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x1x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x1x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x1x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x1x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x2x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x2x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x2x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x2x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x2x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x288x48x32x2x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x288x48x32x2x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x2x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 8, 2, 1, 8, 4, 8, 1, 1, 1, 8>+8
3x288x48x32x2x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x2x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x288x48x32x2x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x288x48x32x2x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+4
3x288x48x32x2x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x2x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x2x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x2x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x2x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+8
3x288x48x32x2x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x2x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x2x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x2x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x2x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x2x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x4x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x288x48x32x4x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+8
3x288x48x32x4x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x288x48x32x4x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x288x48x32x4x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x288x48x32x4x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x288x48x32x4x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+32
3x288x48x32x4x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 128, 32, 32, Default, 8, 4, 1, 8, 8, 8, 8, 1, 1, 2>+-1
3x288x48x32x4x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x4x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x4x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x4x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+8
3x288x48x32x4x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x4x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x4x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x4x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x288x48x32x4x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x288x48x32x4x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x4x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x4x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x4x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x4x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x8x1x1x2x288x10x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x11x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x288x48x32x8x1x1x2x288x12x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x13x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x14x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x15x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x16x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x17x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x18x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x19x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x1x1x2x288x1x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x8x1x1x2x288x20x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x21x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x1x1x2x288x22x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x2x288x23x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x24x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x25x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x26x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x27x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x28x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x2x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x8x1x1x2x288x30x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x2x288x31x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x32x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x33x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x34x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x35x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x36x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x37x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x3x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x8x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x8x1x1x2x288x5x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x6x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x7x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x2x288x9x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x11x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x12x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x13x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x14x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x15x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x8x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x16x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x17x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x8x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x18x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x19x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x1x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x8x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x20x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x21x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x22x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x23x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x24x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x25x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x26x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x27x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x28x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x29x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x2x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x8x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x30x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x31x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x32x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x33x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x34x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x35x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x1x1x3x288x36x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x37x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x3x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x8x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x4x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x5x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x6x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x7x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x8x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x3x288x9x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x288x48x32x8x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x10x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x11x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x12x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x13x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x14x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x8x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x15x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x8x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x16x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x17x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_WaveletModel_CShuffleV3<256l+256m, 128, 128, 32, Default, 8, 2, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x288x48x32x8x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x18x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x19x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 128, 64, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x288x48x32x8x3x3x1x288x1x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x8x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x22x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x23x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x24x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x25x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x26x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x27x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x28x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x29x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x8x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x8x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x31x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x32x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x34x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x35x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x36x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x37x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x288x48x32x8x3x3x1x288x3x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x8x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x288x48x32x8x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x288x48x32x8x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x8x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x288x48x32x8x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x288x48x32x8x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x288x48x32x8x3x3x1x288x8x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x288x48x32x8x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x288x48x32x8x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x9x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x2x128x128x128x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>
3x2x128x128x128x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x2x128x128x128x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>
3x2x128x128x128x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x2x160x56x192x1x1x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>
3x2x160x56x192x1x1x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x2x20x14x24x1x1x1x256x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>
3x2x20x14x24x1x1x1x256x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x2x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x2x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x2x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x2x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+-1
3x2x32x32x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x2x32x32x1x3x3x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x2x32x32x1x3x3x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x2x32x32x1x3x3x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x2x40x28x48x1x1x1x128x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 4, 1, 1>
3x2x40x28x48x1x1x1x128x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x2x80x56x96x1x1x1x64x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 4, 1, 1>
3x2x80x56x96x1x1x1x64x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x320x10x7x12x2x1x2x320x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x320x10x7x12x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x320x10x7x12x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
3x320x10x7x12x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x320x10x7x12x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
3x320x10x7x12x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x10x7x12x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x320x10x7x12x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x320x10x7x12x3x3x3x320x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x320x10x7x12x3x3x3x640x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x10x7x12x3x3x3x640x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x320x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x320x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x15x15x1x3x3x1x192x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x320x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x320x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x320x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x320x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x320x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x320x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x1x1x1x960x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x320x32x32x1x3x3x1x160x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x320x32x32x1x3x3x1x160x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+128
3x320x32x32x1x3x3x1x160x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x320x32x32x1x3x3x1x160x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+-1
3x320x4x4x4x2x2x2x320x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x4x4x4x2x2x2x320x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
3x320x4x4x4x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x4x4x4x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x4x4x4x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x320x4x4x4x3x3x3x320x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x320x4x4x4x3x3x3x320x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
3x320x4x8x4x1x1x1x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x4x8x4x1x1x1x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
3x320x4x8x4x2x1x2x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x320x4x8x4x2x1x2x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+2
3x320x4x8x4x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x4x8x4x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x4x8x4x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x320x4x8x4x3x3x3x320x1x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x4x8x4x3x3x3x320x1x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+1
3x320x5x7x6x2x1x2x320x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x320x5x7x6x2x1x2x320x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
3x320x5x7x6x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x320x5x7x6x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x5x7x6x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x320x5x7x6x3x3x3x320x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x5x7x6x3x3x3x320x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x320x8x8x8x1x1x1x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x1x1x1x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
3x320x8x8x8x1x1x1x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x320x8x8x8x2x1x2x320x1x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x320x8x8x8x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
3x320x8x8x8x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x2x2x2x256x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
3x320x8x8x8x2x2x2x320x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x8x8x8x3x3x3x256x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x3x3x3x256x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
3x320x8x8x8x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x320x8x8x8x3x3x3x256x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+4
3x320x8x8x8x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 2, 1, 1>
3x320x8x8x8x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x320x8x8x8x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x320x8x8x8x3x3x3x320x1x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x8x8x8x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x320x8x8x8x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x320x8x8x8x3x3x3x320x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x320x8x8x8x3x3x3x640x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x3x3x3x640x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+2
3x320x8x8x8x3x3x3x640x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x320x8x8x8x3x3x3x640x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x32x120x160x1x1x1x1x64x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x32x120x160x1x1x1x1x64x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x32x120x160x1x1x1x1x64x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x120x160x1x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
3x32x120x160x1x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+32
3x32x120x160x1x1x1x1x64x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x32x120x160x1x1x1x1x64x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x1x1x1x64x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x32x120x160x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x120x160x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x120x160x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x120x160x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+128
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x32x120x160x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x120x160x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x120x160x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x120x160x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x120x160x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x120x160x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x32x120x160x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x32x120x160x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+64
3x32x120x160x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x120x160x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+64
3x32x128x128x128x1x1x1x2x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x128x128x128x1x1x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x128x128x128x1x1x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 16, Default, 32, 32, 2, 1, 4, 4, 1, 1, 1, 1>
3x32x128x128x128x1x1x1x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 16, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x2x2x2x64x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x2x2x2x64x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x3x3x3x1x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x128x128x128x3x3x3x32x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x128x128x128x3x3x3x32x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x3x3x3x32x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+-1
3x32x128x128x128x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x32x128x128x128x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 1, 2, 4, 4, 1, 1, 4>+-1
3x32x128x128x128x3x3x3x3x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
3x32x128x128x128x3x3x3x64x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x32x128x128x128x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x128x128x128x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
3x32x128x128x128x3x3x3x64x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x32x14x12x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x14x12x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x32x14x12x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x14x12x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x32x14x7x1x5x20x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x14x7x1x5x20x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x14x7x1x5x20x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x14x7x1x5x20x1x1x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x15x15x1x3x3x1x3x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x112x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x112x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x15x15x1x3x3x1x3x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x15x15x1x3x3x1x3x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x15x15x1x3x3x1x3x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x15x15x1x3x3x1x3x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x15x15x1x3x3x1x3x6x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x6x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x15x15x1x3x3x1x3x800x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x800x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x160x56x192x1x1x1x2x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x160x56x192x2x1x2x64x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x160x56x192x3x1x3x1x2x1x0x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x160x56x192x3x1x3x32x2x1x0x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x160x56x192x3x1x3x32x2x1x0x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x160x56x192x3x1x3x32x2x1x0x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x32x160x56x192x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x160x56x192x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x160x56x192x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 4, 1, 2, 4, 2, 4, 4, 1, 1, 4>+128
3x32x160x56x192x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x160x56x192x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 4, 1, 2, 4, 1, 4, 4, 1, 1, 4>+-1
3x32x160x56x192x3x3x3x64x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+64
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x17x17x1x3x3x1x3x100x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x100x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x100x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x16x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x19x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x19x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x19x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x1x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x17x17x1x3x3x1x3x200x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x200x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x200x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x2x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x2x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x32x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x4x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x512x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x58x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x58x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x58x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x59x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x59x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x59x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x64x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x17x17x1x3x3x1x3x6x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x6x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x17x17x1x3x3x1x3x8x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x18x18x1x3x3x1x3x1024x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x1024x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x18x18x1x3x3x1x3x1024x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x1024x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x112x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x112x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x112x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x112x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x114x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x120x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x16x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x19x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x200x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x208x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x208x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x208x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x208x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x24x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x2x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x18x18x1x3x3x1x3x312x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x312x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x312x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x312x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x32x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x400x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x4x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x50x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x56x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x58x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x59x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x624x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x624x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x624x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x624x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x18x18x3x3x3x1x3x4x3x3x1x2x2x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x240x320x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+-1
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 32, 128, 4, Default, 8, 1, 2, 8, 1, 8, 4, 1, 1, 8>+128
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x32x240x320x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+-1
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x240x320x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+-1
3x32x28x13x1x5x20x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x28x13x1x5x20x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x28x13x1x5x20x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x28x13x1x5x20x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x28x23x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x28x23x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x32x28x23x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x28x23x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+-1
3x32x30x30x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x30x30x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+128
3x32x30x30x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x32x30x30x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+128
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x112x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x112x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x30x30x1x3x3x1x3x200x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x200x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x30x30x1x3x3x1x3x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x6x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x6x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x800x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x30x32x1x3x3x1x3x1024x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x1024x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x32x1x3x3x1x3x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x30x32x1x3x3x1x3x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x30x32x1x3x3x1x3x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x30x32x1x3x3x1x3x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x32x1x3x3x1x3x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x30x32x1x3x3x1x3x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x30x32x1x3x3x1x3x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x32x1x3x3x1x3x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x32x1x3x3x1x3x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x30x32x1x3x3x1x3x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x30x32x1x3x3x1x3x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x32x1x3x3x1x3x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x32x1x3x3x1x3x6x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x6x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x30x32x1x3x3x1x3x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x32x1x3x3x1x3x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x32x1x3x3x1x3x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x1024x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x30x36x1x3x3x1x3x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x30x36x1x3x3x1x3x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x30x36x1x3x3x1x3x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x2x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x2x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x2x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x30x36x1x3x3x1x3x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x512x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x512x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x30x36x1x3x3x1x3x6x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x6x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x30x36x1x3x3x1x3x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x30x36x1x3x3x1x3x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x30x36x1x3x3x1x3x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x30x36x1x3x3x1x3x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x1024x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x1024x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x32x30x1x3x3x1x3x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x30x1x3x3x1x3x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x30x1x3x3x1x3x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x30x1x3x3x1x3x400x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x400x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x30x1x3x3x1x3x6x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x6x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x30x1x3x3x1x3x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x32x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x32x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x32x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 16x256x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x32x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x32x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+-1
3x32x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Filter1x1Stride1Pad0, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+128
3x32x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x32x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Filter1x1Stride1Pad0, 8, 1, 2, 8, 2, 8, 4, 1, 1, 8>+128
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x32x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x32x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x128x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x128x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x128x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x16x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x16x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x16x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x1x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x32x32x1x3x3x1x3x1x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x32x32x1x3x3x1x3x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x32x32x1x3x3x1x3x1x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x32x32x1x3x3x1x3x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x2048x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2048x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2048x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x256x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x256x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x2x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x32x32x1x3x3x1x3x2x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x32x32x1x3x3x1x3x2x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x32x32x1x3x3x1x3x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x32x32x1x3x3x1x3x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x32x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x32x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x32x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x4096x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4096x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4096x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x4x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x32x32x1x3x3x1x3x4x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x32x32x1x3x3x1x3x4x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x512x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x512x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x512x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x32x32x1x3x3x1x3x64x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x64x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x64x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x6x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x6x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x3x800x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x800x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x8x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x24x24x0x1x1x1x24x24x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x32x32x1x3x3x1x3x8x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x32x32x1x3x3x1x3x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x3x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x32x32x32x1x5x10x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x32x32x32x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x32x32x32x1x5x10x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x32x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x32x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+128
3x32x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x32x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x32x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+64
3x32x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x32x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+-1
3x32x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x32x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x32x32x1x5x5x1x96x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x32x32x1x5x5x1x96x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x34x34x1x3x3x1x3x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x34x34x1x3x3x1x3x6x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x6x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x36x30x1x3x3x1x3x1024x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x36x30x1x3x3x1x3x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x36x30x1x3x3x1x3x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x30x1x3x3x1x3x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x36x30x1x3x3x1x3x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x36x30x1x3x3x1x3x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x2x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x2x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x2x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x400x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x36x30x1x3x3x1x3x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x512x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x512x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x6x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x6x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x36x30x1x3x3x1x3x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x30x1x3x3x1x3x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x36x30x1x3x3x1x3x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x30x1x3x3x1x3x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x36x36x1x3x3x1x3x128x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x128x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x36x36x1x3x3x1x3x128x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x128x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x36x36x1x3x3x1x3x12x3x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x12x3x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x12x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x12x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x16x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x16x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x1x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x1x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x36x36x1x3x3x1x3x1x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x1x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x36x36x1x3x3x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x36x1x3x3x1x3x2x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x2x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x36x36x1x3x3x1x3x2x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x36x36x1x3x3x1x3x2x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x36x1x3x3x1x3x48x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x48x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x4x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x4x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x36x36x1x3x3x1x3x4x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x4x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x36x36x1x3x3x1x3x512x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x64x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x64x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x36x36x1x3x3x1x3x64x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x64x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x36x36x1x3x3x1x3x6x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x36x36x1x3x3x1x3x6x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x36x36x1x3x3x1x3x8x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x8x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x36x36x1x3x3x1x3x8x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x36x36x1x3x3x1x3x8x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x32x480x640x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x1024x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x1024x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x8x8x1x3x3x1x3x1024x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x1024x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x128x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x16x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x8x8x1x3x3x1x3x1x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x1x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x8x8x1x3x3x1x3x1x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x1x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 1, 1, 1, 1, 1>+4
3x32x8x8x1x3x3x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x8x8x1x3x3x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x8x8x1x3x3x1x3x2x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x2x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x32x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x8x8x1x3x3x1x3x4x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x4x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x8x8x1x3x3x1x3x4x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x4x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x50x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x64x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x8x8x1x3x3x1x3x8x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x8x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x8x8x1x3x3x1x3x8x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x8x8x1x3x3x1x3x8x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1024x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x128x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x16x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+32
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x1x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+4
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2048x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+128
3x32x9x9x1x3x3x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+8
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x2x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x32x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+64
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4096x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x4x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+8
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 32, 32, 8, 8, Default, 32, 32, 2, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x512x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 1, 1, 1>
3x32x9x9x1x3x3x1x3x64x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+16
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 4, 1, 1, 1>
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+16
3x336x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x336x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x340x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>
3x340x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x340x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>
3x340x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x384x15x15x1x3x3x1x288x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x15x15x1x3x3x1x288x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x384x15x15x1x3x3x1x288x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x15x15x1x3x3x1x288x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+8
3x384x15x15x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x15x15x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+8
3x384x15x15x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x15x15x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+8
3x384x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x384x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x384x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+16
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x384x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x384x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x384x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x384x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x384x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x1x3x1x384x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x1x1x384x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+-1
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 128, 256, 4, Default, 8, 2, 4, 8, 2, 8, 4, 1, 1, 8>+-1
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+16
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x384x32x32x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x384x32x32x1x3x3x1x384x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x384x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x384x32x32x1x3x3x1x448x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x448x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+32
3x384x32x32x1x3x3x1x448x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x384x32x32x1x3x3x1x448x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x3x128x128x128x16x16x16x1536x1x0x0x0x16x16x16x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x128x128x128x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x128x128x128x1x1x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 1, 4, 1, 1>
3x3x128x128x128x1x1x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x3x128x128x128x1x1x1x64x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x128x128x128x3x3x3x32x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x15x15x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x15x15x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x3x15x15x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x15x15x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x3x16x16x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x16x16x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x3x16x16x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x16x16x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x3x30x30x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x30x30x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x30x30x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x30x30x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x32x32x1x11x11x1x64x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x11x11x1x64x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x11x11x1x64x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x11x11x1x64x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x1x1x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x32x32x1x1x1x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x1x1x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 64, BlkTile: 16x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
3x3x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x3x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x3x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x3x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 1x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x3x32x32x1x3x3x1x24x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x24x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x200x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2048x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x312x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x400x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4096x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x58x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x59x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x624x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 16, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x6x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 1, 1, 4, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x32x32x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x4x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x5x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x3x32x32x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Default, 16, 16, 1, 4, 1, 8, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x32x32x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x64x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x7x7x1x96x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, 1>+-1
3x3x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x3x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 1, 8, 1, 1>
3x3x480x640x1x3x3x1x16x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<64, 48, 64, 32, Default, 8, 3, 4, 3, 4, 4, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, 1>+-1
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x432x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x432x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x448x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x448x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x448x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x448x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x448x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x448x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x448x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x448x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x448x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x448x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x464x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x464x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x120x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 2, 1, 1>
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 128, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x480x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x480x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x48x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x48x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x48x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x48x32x32x1x1x1x1x832x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Filter1x1Stride1Pad0, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x48x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x48x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x48x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x48x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x48x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x48x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x48x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x48x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x48x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x48x32x32x1x5x5x1x512x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x5x5x1x512x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 64, 128, 4, Default, 8, 2, 2, 8, 2, 8, 4, 1, 1, 8>+64
3x48x32x32x1x5x5x1x512x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x48x32x32x1x5x5x1x512x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 64, 128, 4, Default, 8, 2, 2, 8, 2, 8, 4, 1, 1, 8>+64
3x48x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x48x32x32x1x5x5x1x64x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x4x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x4x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x4x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x4x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x4x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x4x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x4x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x4x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x4x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x4x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x4x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 1, 1, 1>
3x4x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x4x32x32x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 16, 4, 4, Default, 16, 16, 1, 1, 4, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x4x32x32x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x4x32x32x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 1, 2, 1, 1, 1, 1>
3x510x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>
3x510x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x510x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>
3x510x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x510x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>
3x510x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x510x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Default, 32, 32, 1, 2, 1, 8, 1, 1>
3x510x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+32
3x512x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x3x3x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x15x15x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x15x15x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x15x15x1x5x5x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x16x16x16x1x1x1x1024x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x16x16x16x1x1x1x1024x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+-1
3x512x16x16x16x2x2x2x1536x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x512x16x16x16x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x16x16x16x2x2x2x256x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x512x16x16x16x3x3x3x1024x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x16x16x16x3x3x3x1024x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+1
3x512x16x16x16x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x512x16x16x16x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x512x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x512x16x16x16x3x3x3x512x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 4, 2, 1, 4, 4, 4, 1, 1, 1, 4>+-1
3x512x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x512x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+16
3x512x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 128, 32, 8, 8, Default, 32, 32, 2, 2, 8, 8, 1, 1>
3x512x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x512x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x512x16x16x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x512x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x512x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x512x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x3x3x1x256x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+16
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 8, 1, 1>
3x512x16x16x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+16
3x512x20x14x24x3x3x3x256x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x512x30x30x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x30x30x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x512x30x30x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x30x30x1x3x3x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x512x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x512x32x32x1x1x1x1x112x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+64
3x512x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x144x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x16x64, WaveTile: 16x16, WaveMap: 4x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+128
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+32
3x512x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 16, 64, Filter1x1Pad0, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x512x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x512x32x32x1x3x3x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x512x32x32x1x3x3x1x510x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x512x32x32x1x3x3x1x510x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+32
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 32, 64, 4, Default, 8, 1, 2, 2, 2, 8, 4, 1, 1, 8>+32
3x512x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 256, 128, 4, Default, 8, 4, 2, 8, 4, 8, 2, 1, 1, 8>+32
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x3x3x1x512x256x4x4x0x1x1x1x4x4x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 128, 4, Default, 8, 4, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x512x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x512x32x32x32x1x1x1x256x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 4, 4, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x512x32x32x32x3x3x3x256x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x528x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x528x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+128
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 32, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x528x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 32, 32, Filter1x1Stride1Pad0, 8, 2, 1, 4, 4, 4, 4, 1, 1, 2>+-1
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x54x16x16x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x54x16x16x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x54x16x16x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Default, 32, 32, 2, 2, 1, 1, 1, 1>
3x54x16x16x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x54x32x32x1x1x1x1x216x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x54x32x32x1x1x1x1x216x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x54x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x54x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x54x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x54x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x54x32x32x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Xdl_CShuffle_Large_Tensor<256, 256, 128, 32, Default, 32, 32, 4, 2, 2, 2, 2, 1, 1>
3x54x32x32x1x3x3x1x54x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x576x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x576x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x576x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x576x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x576x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x576x32x32x1x1x1x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x58x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 16, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 1, 4, 1, 8, 1, 1>
3x58x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x58x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x58x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x32x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 2x4, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 1, 1>
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
3x58x32x32x1x1x1x1x58x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffleV3_Large_Tensor<256, 128, 64, 32, 8, 8, Default, 32, 32, 2, 1, 1, 1, 1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x608x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x60x16x16x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x60x16x16x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x60x16x16x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x60x16x16x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 2, 1, 8, 1, 1>
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x60x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Filter1x1Stride1Pad0, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+-1
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 2, 1, 1>
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 64, 80, 32, Default, 8, 4, 5, 4, 4, 5, 4, 1, 1, 2>+128
3x60x32x32x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x60x32x32x1x3x3x1x60x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
3x624x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x624x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x640x10x7x12x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x640x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x640x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x640x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x640x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x640x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x640x8x8x8x3x3x3x320x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x640x8x8x8x3x3x3x320x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Default, 16, 16, 1, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x10x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x1x1x1x32x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x1x1x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x120x160x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x120x160x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x120x160x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 64, 64, Default, 16, 16, 1, 2, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x120x160x1x3x3x1x32x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x128x128x128x1x1x1x128x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x128x128x128x1x1x1x128x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x128x128x128x1x1x1x2x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x128x128x128x1x1x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Filter1x1Stride1Pad0, 8, 1, 1, 4, 4, 1, 4, 1, 1, 1>+128
3x64x128x128x128x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 16, Default, 32, 32, 4, 2, 4, 4, 4, 1, 1, 1>
3x64x128x128x128x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x64x128x128x128x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+-1
3x64x128x128x128x3x3x3x32x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x128x128x128x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x128x128x128x3x3x3x3x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1>+-1
3x64x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x128x128x128x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+-1
3x64x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x64x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x64x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x15x15x1x3x3x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x15x15x1x5x5x1x1x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x15x15x1x5x5x1x1x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x15x15x1x5x5x1x1x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x15x15x1x5x5x1x1x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x15x15x1x7x7x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x64x15x15x1x7x7x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x15x15x1x7x7x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x64x15x15x1x7x7x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x160x56x192x3x3x3x32x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 32, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x64x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x64x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x28x28x16x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x28x28x16x1x1x5x64x1x0x0x2x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x28x28x16x1x1x7x64x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x28x28x4x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x28x28x4x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x64x28x28x4x1x1x5x64x1x0x0x2x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x64x28x28x4x1x1x7x64x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x64x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x64x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 1, 1, 1>
3x64x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x30x30x1x5x5x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x30x30x1x5x5x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x30x30x1x5x5x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x30x30x1x5x5x1x1x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x64x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+128
3x64x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x64x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x64x32x32x1x1x1x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x1x1x1x1x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x256x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x64x32x32x1x1x1x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Default, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x2x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x64x32x32x1x1x1x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x1x1x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 1, 1>
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Filter1x1Stride1Pad0, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 64x16x64, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+64
3x64x32x32x1x1x1x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x80x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x7x1x64x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x32x32x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x64x32x32x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x64x32x32x1x3x3x1x13x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x32x32x1x3x3x1x13x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x13x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x32x32x1x3x3x1x13x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x192x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x24x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x32x32x1x3x3x1x24x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x24x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x24x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 64, 128, 4, Default, 8, 2, 2, 8, 2, 8, 4, 1, 1, 8>+64
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 64, 128, 4, Default, 8, 2, 2, 8, 2, 8, 4, 1, 1, 8>+64
3x64x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x64x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x3x3x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x96x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x64x32x32x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x64x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x5x5x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x32x32x1x5x5x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x64x32x32x1x5x5x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Default, 32, 32, 2, 4, 8, 4, 1, 1>
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x5x5x1x192x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+64
3x64x32x32x1x5x5x1x24x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x32x32x1x5x5x1x24x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x5x5x1x24x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x5x5x1x24x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+-1
3x64x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 64, 4, Default, 8, 2, 2, 8, 4, 8, 4, 1, 1, 8>+128
3x64x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x32x32x1x5x5x1x48x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x7x1x1x64x256x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x56x56x16x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x56x56x16x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x56x56x4x1x1x3x64x1x0x0x1x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x56x56x4x1x1x7x64x1x0x0x3x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x60x80x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x12x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x60x80x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x14x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x2x2x1x64x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x60x80x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x60x80x1x2x2x1x64x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x60x80x1x3x3x1x64x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x60x80x1x3x3x1x64x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x60x80x1x3x3x1x64x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 2, 8, 2, 8, 1, 1, 2, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 64, 32, Default, 16, 16, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x60x80x1x3x3x1x64x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+64
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+16
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Default, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 32, 4, Default, 8, 2, 1, 8, 4, 8, 1, 1, 1, 8>+16
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 64, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<64, 64, 32, 4, Default, 8, 2, 1, 8, 4, 8, 2, 1, 1, 8>+32
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x64x60x80x1x3x3x1x64x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x64x64x64x64x1x1x1x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Filter1x1Pad0, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x1x1x1x32x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 32, 8, 8, Default, 16, 16, 1, 1, 8, 8, 1, 1>
3x64x64x64x64x1x1x1x32x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x2x2x2x128x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x2x2x2x32x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 16, 4, 4, Default, 32, 32, 1, 1, 4, 8, 1, 1>
3x64x64x64x64x2x2x2x32x1x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x2x2x2x32x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x64x64x64x2x2x2x32x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x64x64x64x64x3x3x3x128x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x64x64x64x64x3x3x3x128x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x64x64x64x64x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x64x64x64x64x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 16, Default, 32, 32, 2, 2, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x3x3x3x32x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x64x64x64x64x3x3x3x32x1x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x3x3x3x32x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x64x64x64x3x3x3x32x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x64x64x64x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x3x3x3x64x1x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x64x64x64x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x64x64x64x64x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x64x64x64x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 4, 4, 4, 4, 1, 1, 4>+-1
3x64x6x6x1x11x11x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x64x6x6x1x11x11x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x64x6x6x1x11x11x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<64, 64, 16, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x64x6x6x1x11x11x1x3x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x64x7x7x1x11x11x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x7x7x1x11x11x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 1, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x64x7x7x1x11x11x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Default, 16, 16, 1, 1, 16, 1, 1, 1>
3x64x7x7x1x11x11x1x3x256x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+64
3x64x80x56x96x1x1x1x2x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 32, 16, 64, Filter1x1Pad0, 16, 16, 1, 1, 4, 4, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x64x80x56x96x2x1x2x32x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x80x56x96x2x1x2x32x2x0x0x0x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+128
3x64x80x56x96x2x2x2x128x2x0x0x0x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x64x80x56x96x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 2, 1, 1>
3x64x80x56x96x3x3x3x128x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 128, 4, Default, 4, 1, 2, 4, 1, 4, 2, 1, 1, 4>+-1
3x64x80x56x96x3x3x3x128x2x1x1x1x2x2x2x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 16, Default, 32, 32, 1, 2, 4, 4, 4, 1, 1, 1>
3x64x80x56x96x3x3x3x32x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x80x56x96x3x3x3x32x2x1x1x1x2x1x2x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x64x80x56x96x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 8, 1, 1>
3x64x80x56x96x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 64, 16, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, 1>
3x64x80x56x96x3x3x3x64x2x1x1x1x1x1x1x1x1x1x0x1xNCDHWxFP32xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<256, 64, 64, 8, Default, 8, 1, 1, 1, 4, 4, 4, 1, 1, 4>+-1
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x672x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x672x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x704x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x720x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x720x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x736x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x768x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x768x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x800x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x80x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x80x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x80x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 1, 1>
3x80x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+-1
3x80x32x32x1x3x3x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x80x32x32x1x3x3x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x816x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x816x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x832x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x832x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x832x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x832x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x832x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x832x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 64, 64, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
3x832x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x832x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x832x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x864x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x864x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x864x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v5, BlkGemmPipelinePrefetchStages: 3>+-1
3x896x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x896x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x896x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x896x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x912x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x912x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x928x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+64
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x960x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+32
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x960x32x32x1x1x1x1x160x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 256x256x32, WaveTile: 32x32, WaveMap: 4x4, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x960x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x960x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x960x32x32x1x1x1x1x240x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x960x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x960x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x96x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x13x13x1x7x7x1x3x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x96x15x15x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x15x15x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x96x15x15x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x15x15x1x3x3x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffleV3<64, 32, 64, 32, Default, 8, 1, 2, 4, 4, 4, 4, 1, 1, 2>+-1
3x96x15x15x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x15x15x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x96x15x15x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x15x15x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+64
3x96x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x96x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x96x30x30x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x30x30x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x30x30x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x30x30x1x3x3x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 64, 128, 32, Filter1x1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 64, 16, 64, 16, 16, Filter1x1Stride1Pad0, 16, 16, 1, 1, 16, 8, 1, 1>
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<64, 16, 16, 128, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<Default, CRR> BlkSize: 128, BlkTile: 32x16x64, WaveTile: 16x16, WaveMap: 1x1, VmemReadVec: 4x2, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 3>+64
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x24x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<128, 16, 32, 64, Filter1x1Stride1Pad0, 16, 16, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4, BlkGemmPipelinePrefetchStages: 3>+-1
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+128
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1>
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 256, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 2, 4, 8, 4, 1, 1>
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 128, 32, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x96x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x208x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x208x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 128, 256, 32, Default, 32, 32, 2, 4, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 8, 1, 1>
3x96x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x96x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x96x32x32x1x3x3x1x96x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Default, 32, 32, 4, 2, 8, 8, 1, 1>
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x96x32x32x1x3x3x1x96x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+-1
3x96x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x96x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 64, 16, 16, Default, 32, 32, 1, 1, 16, 2, 1, 1>
3x96x32x32x1x5x5x1x32x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Xdl_CShuffle<128, 128, 64, 4, Default, 8, 2, 2, 8, 4, 8, 2, 1, 1, 8>+128
3x96x32x32x1x7x7x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x32x32x1x7x7x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+-1
3x96x32x32x1x7x7x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 128, 32, 32, 8, 8, Default, 32, 32, 1, 1, 8, 1, 1, 1>
3x96x32x32x1x7x7x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Xdl_CShuffle<256, 64, 64, 64, Default, 8, 1, 1, 4, 8, 1, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+128
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Xdl_CShuffle_v1<256, 256, 128, 32, 8, 8, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 1, 1>
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v4>
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x128x64, WaveTile: 32x32, WaveMap: 2x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3, BlkGemmPipelinePrefetchStages: 2>+-1
